Upload task output 0353de22-df95-4ff9-a6a0-d97156bde1a9
Browse files- README.md +68 -0
- adapter_config.json +42 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +4 -0
- chat_template.jinja +5 -0
- checkpoint-400/README.md +210 -0
- checkpoint-400/adapter_config.json +42 -0
- checkpoint-400/adapter_model.safetensors +3 -0
- checkpoint-400/added_tokens.json +4 -0
- checkpoint-400/chat_template.jinja +5 -0
- checkpoint-400/optimizer.pt +3 -0
- checkpoint-400/rng_state_0.pth +3 -0
- checkpoint-400/rng_state_1.pth +3 -0
- checkpoint-400/scheduler.pt +3 -0
- checkpoint-400/special_tokens_map.json +30 -0
- checkpoint-400/tokenizer.json +0 -0
- checkpoint-400/tokenizer.model +3 -0
- checkpoint-400/tokenizer_config.json +62 -0
- checkpoint-400/trainer_state.json +649 -0
- checkpoint-400/training_args.bin +3 -0
- config.json +26 -0
- generation_config.json +7 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +747 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +62 -0
README.md
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
model_name: 4a66a896-d828-4815-ac5b-89dddef44f66
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
- trl
|
| 7 |
+
- dpo
|
| 8 |
+
licence: license
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Model Card for 4a66a896-d828-4815-ac5b-89dddef44f66
|
| 12 |
+
|
| 13 |
+
This model is a fine-tuned version of [None](https://huggingface.co/None).
|
| 14 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 15 |
+
|
| 16 |
+
## Quick start
|
| 17 |
+
|
| 18 |
+
```python
|
| 19 |
+
from transformers import pipeline
|
| 20 |
+
|
| 21 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 22 |
+
generator = pipeline("text-generation", model="None", device="cuda")
|
| 23 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 24 |
+
print(output["generated_text"])
|
| 25 |
+
```
|
| 26 |
+
|
| 27 |
+
## Training procedure
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
|
| 33 |
+
|
| 34 |
+
### Framework versions
|
| 35 |
+
|
| 36 |
+
- TRL: 0.21.0
|
| 37 |
+
- Transformers: 4.55.0
|
| 38 |
+
- Pytorch: 2.7.1+cu128
|
| 39 |
+
- Datasets: 4.0.0
|
| 40 |
+
- Tokenizers: 0.21.4
|
| 41 |
+
|
| 42 |
+
## Citations
|
| 43 |
+
|
| 44 |
+
Cite DPO as:
|
| 45 |
+
|
| 46 |
+
```bibtex
|
| 47 |
+
@inproceedings{rafailov2023direct,
|
| 48 |
+
title = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
|
| 49 |
+
author = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
|
| 50 |
+
year = 2023,
|
| 51 |
+
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
|
| 52 |
+
url = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
|
| 53 |
+
editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
|
| 54 |
+
}
|
| 55 |
+
```
|
| 56 |
+
|
| 57 |
+
Cite TRL as:
|
| 58 |
+
|
| 59 |
+
```bibtex
|
| 60 |
+
@misc{vonwerra2022trl,
|
| 61 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
| 62 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
|
| 63 |
+
year = 2020,
|
| 64 |
+
journal = {GitHub repository},
|
| 65 |
+
publisher = {GitHub},
|
| 66 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 67 |
+
}
|
| 68 |
+
```
|
adapter_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "dltjdgh0928/test_instruction",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": null,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 64,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 32,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"k_proj",
|
| 29 |
+
"o_proj",
|
| 30 |
+
"down_proj",
|
| 31 |
+
"q_proj",
|
| 32 |
+
"gate_proj",
|
| 33 |
+
"v_proj",
|
| 34 |
+
"up_proj"
|
| 35 |
+
],
|
| 36 |
+
"target_parameters": [],
|
| 37 |
+
"task_type": "CAUSAL_LM",
|
| 38 |
+
"trainable_token_indices": null,
|
| 39 |
+
"use_dora": false,
|
| 40 |
+
"use_qalora": false,
|
| 41 |
+
"use_rslora": false
|
| 42 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3727ca325f5f315707e769dd30804f726ec738867ebf91dbfccc5d9376b2a92
|
| 3 |
+
size 335604696
|
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|im_end|>": 32000,
|
| 3 |
+
"<|im_start|>": 32001
|
| 4 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
|
| 2 |
+
|
| 3 |
+
'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
|
| 4 |
+
|
| 5 |
+
' }}{% endif %}
|
checkpoint-400/README.md
ADDED
|
@@ -0,0 +1,210 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: /cache/models/dltjdgh0928--test_instruction
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- axolotl
|
| 7 |
+
- base_model:adapter:/cache/models/dltjdgh0928--test_instruction
|
| 8 |
+
- dpo
|
| 9 |
+
- lora
|
| 10 |
+
- transformers
|
| 11 |
+
- trl
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# Model Card for Model ID
|
| 15 |
+
|
| 16 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
## Model Details
|
| 21 |
+
|
| 22 |
+
### Model Description
|
| 23 |
+
|
| 24 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
|
| 28 |
+
- **Developed by:** [More Information Needed]
|
| 29 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 30 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 31 |
+
- **Model type:** [More Information Needed]
|
| 32 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 33 |
+
- **License:** [More Information Needed]
|
| 34 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
### Model Sources [optional]
|
| 37 |
+
|
| 38 |
+
<!-- Provide the basic links for the model. -->
|
| 39 |
+
|
| 40 |
+
- **Repository:** [More Information Needed]
|
| 41 |
+
- **Paper [optional]:** [More Information Needed]
|
| 42 |
+
- **Demo [optional]:** [More Information Needed]
|
| 43 |
+
|
| 44 |
+
## Uses
|
| 45 |
+
|
| 46 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 47 |
+
|
| 48 |
+
### Direct Use
|
| 49 |
+
|
| 50 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 51 |
+
|
| 52 |
+
[More Information Needed]
|
| 53 |
+
|
| 54 |
+
### Downstream Use [optional]
|
| 55 |
+
|
| 56 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 57 |
+
|
| 58 |
+
[More Information Needed]
|
| 59 |
+
|
| 60 |
+
### Out-of-Scope Use
|
| 61 |
+
|
| 62 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 63 |
+
|
| 64 |
+
[More Information Needed]
|
| 65 |
+
|
| 66 |
+
## Bias, Risks, and Limitations
|
| 67 |
+
|
| 68 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 69 |
+
|
| 70 |
+
[More Information Needed]
|
| 71 |
+
|
| 72 |
+
### Recommendations
|
| 73 |
+
|
| 74 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 75 |
+
|
| 76 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 77 |
+
|
| 78 |
+
## How to Get Started with the Model
|
| 79 |
+
|
| 80 |
+
Use the code below to get started with the model.
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
## Training Details
|
| 85 |
+
|
| 86 |
+
### Training Data
|
| 87 |
+
|
| 88 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
### Training Procedure
|
| 93 |
+
|
| 94 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 95 |
+
|
| 96 |
+
#### Preprocessing [optional]
|
| 97 |
+
|
| 98 |
+
[More Information Needed]
|
| 99 |
+
|
| 100 |
+
|
| 101 |
+
#### Training Hyperparameters
|
| 102 |
+
|
| 103 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 104 |
+
|
| 105 |
+
#### Speeds, Sizes, Times [optional]
|
| 106 |
+
|
| 107 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 108 |
+
|
| 109 |
+
[More Information Needed]
|
| 110 |
+
|
| 111 |
+
## Evaluation
|
| 112 |
+
|
| 113 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 114 |
+
|
| 115 |
+
### Testing Data, Factors & Metrics
|
| 116 |
+
|
| 117 |
+
#### Testing Data
|
| 118 |
+
|
| 119 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 120 |
+
|
| 121 |
+
[More Information Needed]
|
| 122 |
+
|
| 123 |
+
#### Factors
|
| 124 |
+
|
| 125 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 126 |
+
|
| 127 |
+
[More Information Needed]
|
| 128 |
+
|
| 129 |
+
#### Metrics
|
| 130 |
+
|
| 131 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 132 |
+
|
| 133 |
+
[More Information Needed]
|
| 134 |
+
|
| 135 |
+
### Results
|
| 136 |
+
|
| 137 |
+
[More Information Needed]
|
| 138 |
+
|
| 139 |
+
#### Summary
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
|
| 143 |
+
## Model Examination [optional]
|
| 144 |
+
|
| 145 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 146 |
+
|
| 147 |
+
[More Information Needed]
|
| 148 |
+
|
| 149 |
+
## Environmental Impact
|
| 150 |
+
|
| 151 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 152 |
+
|
| 153 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 154 |
+
|
| 155 |
+
- **Hardware Type:** [More Information Needed]
|
| 156 |
+
- **Hours used:** [More Information Needed]
|
| 157 |
+
- **Cloud Provider:** [More Information Needed]
|
| 158 |
+
- **Compute Region:** [More Information Needed]
|
| 159 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 160 |
+
|
| 161 |
+
## Technical Specifications [optional]
|
| 162 |
+
|
| 163 |
+
### Model Architecture and Objective
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
### Compute Infrastructure
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
#### Hardware
|
| 172 |
+
|
| 173 |
+
[More Information Needed]
|
| 174 |
+
|
| 175 |
+
#### Software
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
## Citation [optional]
|
| 180 |
+
|
| 181 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 182 |
+
|
| 183 |
+
**BibTeX:**
|
| 184 |
+
|
| 185 |
+
[More Information Needed]
|
| 186 |
+
|
| 187 |
+
**APA:**
|
| 188 |
+
|
| 189 |
+
[More Information Needed]
|
| 190 |
+
|
| 191 |
+
## Glossary [optional]
|
| 192 |
+
|
| 193 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## More Information [optional]
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
## Model Card Authors [optional]
|
| 202 |
+
|
| 203 |
+
[More Information Needed]
|
| 204 |
+
|
| 205 |
+
## Model Card Contact
|
| 206 |
+
|
| 207 |
+
[More Information Needed]
|
| 208 |
+
### Framework versions
|
| 209 |
+
|
| 210 |
+
- PEFT 0.17.0
|
checkpoint-400/adapter_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/cache/models/dltjdgh0928--test_instruction",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": null,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 64,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 32,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"v_proj",
|
| 29 |
+
"o_proj",
|
| 30 |
+
"down_proj",
|
| 31 |
+
"k_proj",
|
| 32 |
+
"gate_proj",
|
| 33 |
+
"q_proj",
|
| 34 |
+
"up_proj"
|
| 35 |
+
],
|
| 36 |
+
"target_parameters": [],
|
| 37 |
+
"task_type": "CAUSAL_LM",
|
| 38 |
+
"trainable_token_indices": null,
|
| 39 |
+
"use_dora": false,
|
| 40 |
+
"use_qalora": false,
|
| 41 |
+
"use_rslora": false
|
| 42 |
+
}
|
checkpoint-400/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63e54db9cc731dc5468fd70dc22bf8b839e4c96acf3b394d3fdd1fe753464c9e
|
| 3 |
+
size 335604696
|
checkpoint-400/added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|im_end|>": 32000,
|
| 3 |
+
"<|im_start|>": 32001
|
| 4 |
+
}
|
checkpoint-400/chat_template.jinja
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
|
| 2 |
+
|
| 3 |
+
'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
|
| 4 |
+
|
| 5 |
+
' }}{% endif %}
|
checkpoint-400/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f842d54709a70720497779fc32963dfb5a66258b6f42ef1d266dfa36cc23503
|
| 3 |
+
size 170921189
|
checkpoint-400/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4dd7671ce88d469c49c0530724ac76b2306574002d1ecd1ca9294e41621fd96a
|
| 3 |
+
size 14917
|
checkpoint-400/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3246ef1170ccca541a03b89ad6f20e01c51eb6834a2c2211c78c71c70f896879
|
| 3 |
+
size 14917
|
checkpoint-400/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ac2dfafea8813ec095ae0eab7f826db55bf978f3f1d5730f62da524dbde5525
|
| 3 |
+
size 1465
|
checkpoint-400/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
checkpoint-400/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-400/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
checkpoint-400/tokenizer_config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "<|im_end|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"32001": {
|
| 39 |
+
"content": "<|im_start|>",
|
| 40 |
+
"lstrip": true,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": true,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
}
|
| 46 |
+
},
|
| 47 |
+
"additional_special_tokens": [],
|
| 48 |
+
"bos_token": "<s>",
|
| 49 |
+
"clean_up_tokenization_spaces": false,
|
| 50 |
+
"eos_token": "</s>",
|
| 51 |
+
"extra_special_tokens": {},
|
| 52 |
+
"legacy": true,
|
| 53 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 54 |
+
"pad_token": "</s>",
|
| 55 |
+
"sp_model_kwargs": {},
|
| 56 |
+
"spaces_between_special_tokens": false,
|
| 57 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 58 |
+
"trust_remote_code": false,
|
| 59 |
+
"unk_token": "<unk>",
|
| 60 |
+
"use_default_system_prompt": true,
|
| 61 |
+
"use_fast": true
|
| 62 |
+
}
|
checkpoint-400/trainer_state.json
ADDED
|
@@ -0,0 +1,649 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.12861736334405144,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 400,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0003215434083601286,
|
| 14 |
+
"grad_norm": 42.437408447265625,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"logits/chosen": -2.349905014038086,
|
| 17 |
+
"logits/rejected": -2.3399078845977783,
|
| 18 |
+
"logps/chosen": -263.0742492675781,
|
| 19 |
+
"logps/rejected": -220.2288055419922,
|
| 20 |
+
"loss": 0.6931,
|
| 21 |
+
"rewards/accuracies": 0.0,
|
| 22 |
+
"rewards/chosen": 0.0,
|
| 23 |
+
"rewards/margins": 0.0,
|
| 24 |
+
"rewards/rejected": 0.0,
|
| 25 |
+
"step": 1
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.003215434083601286,
|
| 29 |
+
"grad_norm": 15.105825424194336,
|
| 30 |
+
"learning_rate": 1.35e-06,
|
| 31 |
+
"logits/chosen": -2.3186473846435547,
|
| 32 |
+
"logits/rejected": -2.2896101474761963,
|
| 33 |
+
"logps/chosen": -291.5194091796875,
|
| 34 |
+
"logps/rejected": -251.97914123535156,
|
| 35 |
+
"loss": 0.6414,
|
| 36 |
+
"rewards/accuracies": 0.569444477558136,
|
| 37 |
+
"rewards/chosen": 0.6907879114151001,
|
| 38 |
+
"rewards/margins": 0.17508786916732788,
|
| 39 |
+
"rewards/rejected": 0.5157000422477722,
|
| 40 |
+
"step": 10
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.006430868167202572,
|
| 44 |
+
"grad_norm": 24.082569122314453,
|
| 45 |
+
"learning_rate": 2.8500000000000002e-06,
|
| 46 |
+
"logits/chosen": -2.293513059616089,
|
| 47 |
+
"logits/rejected": -2.2872815132141113,
|
| 48 |
+
"logps/chosen": -282.1536865234375,
|
| 49 |
+
"logps/rejected": -247.08609008789062,
|
| 50 |
+
"loss": 0.4722,
|
| 51 |
+
"rewards/accuracies": 0.7732143402099609,
|
| 52 |
+
"rewards/chosen": 1.9890003204345703,
|
| 53 |
+
"rewards/margins": 1.0885450839996338,
|
| 54 |
+
"rewards/rejected": 0.900455117225647,
|
| 55 |
+
"step": 20
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.00964630225080386,
|
| 59 |
+
"grad_norm": 16.065027236938477,
|
| 60 |
+
"learning_rate": 4.35e-06,
|
| 61 |
+
"logits/chosen": -2.259777784347534,
|
| 62 |
+
"logits/rejected": -2.2146363258361816,
|
| 63 |
+
"logps/chosen": -290.0853271484375,
|
| 64 |
+
"logps/rejected": -265.5473937988281,
|
| 65 |
+
"loss": 0.3727,
|
| 66 |
+
"rewards/accuracies": 0.8125,
|
| 67 |
+
"rewards/chosen": 1.2093960046768188,
|
| 68 |
+
"rewards/margins": 2.074486017227173,
|
| 69 |
+
"rewards/rejected": -0.8650901913642883,
|
| 70 |
+
"step": 30
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.012861736334405145,
|
| 74 |
+
"grad_norm": 18.36149787902832,
|
| 75 |
+
"learning_rate": 5.850000000000001e-06,
|
| 76 |
+
"logits/chosen": -2.249405860900879,
|
| 77 |
+
"logits/rejected": -2.229692220687866,
|
| 78 |
+
"logps/chosen": -279.88031005859375,
|
| 79 |
+
"logps/rejected": -274.5915222167969,
|
| 80 |
+
"loss": 0.3086,
|
| 81 |
+
"rewards/accuracies": 0.848214328289032,
|
| 82 |
+
"rewards/chosen": 1.447776436805725,
|
| 83 |
+
"rewards/margins": 2.8266141414642334,
|
| 84 |
+
"rewards/rejected": -1.3788377046585083,
|
| 85 |
+
"step": 40
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.01607717041800643,
|
| 89 |
+
"grad_norm": 20.32265281677246,
|
| 90 |
+
"learning_rate": 7.35e-06,
|
| 91 |
+
"logits/chosen": -2.288564682006836,
|
| 92 |
+
"logits/rejected": -2.294003963470459,
|
| 93 |
+
"logps/chosen": -306.5020446777344,
|
| 94 |
+
"logps/rejected": -297.538330078125,
|
| 95 |
+
"loss": 0.2908,
|
| 96 |
+
"rewards/accuracies": 0.8446429371833801,
|
| 97 |
+
"rewards/chosen": -0.050978630781173706,
|
| 98 |
+
"rewards/margins": 3.4700608253479004,
|
| 99 |
+
"rewards/rejected": -3.5210394859313965,
|
| 100 |
+
"step": 50
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.01929260450160772,
|
| 104 |
+
"grad_norm": 20.51503562927246,
|
| 105 |
+
"learning_rate": 8.85e-06,
|
| 106 |
+
"logits/chosen": -2.354025363922119,
|
| 107 |
+
"logits/rejected": -2.354628324508667,
|
| 108 |
+
"logps/chosen": -310.90704345703125,
|
| 109 |
+
"logps/rejected": -308.752197265625,
|
| 110 |
+
"loss": 0.2859,
|
| 111 |
+
"rewards/accuracies": 0.8767857551574707,
|
| 112 |
+
"rewards/chosen": -1.1099927425384521,
|
| 113 |
+
"rewards/margins": 3.521933078765869,
|
| 114 |
+
"rewards/rejected": -4.631926536560059,
|
| 115 |
+
"step": 60
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.022508038585209004,
|
| 119 |
+
"grad_norm": 24.096118927001953,
|
| 120 |
+
"learning_rate": 1.035e-05,
|
| 121 |
+
"logits/chosen": -2.4225921630859375,
|
| 122 |
+
"logits/rejected": -2.405019760131836,
|
| 123 |
+
"logps/chosen": -298.91473388671875,
|
| 124 |
+
"logps/rejected": -305.43634033203125,
|
| 125 |
+
"loss": 0.2776,
|
| 126 |
+
"rewards/accuracies": 0.8660715222358704,
|
| 127 |
+
"rewards/chosen": -0.6255666613578796,
|
| 128 |
+
"rewards/margins": 4.037406921386719,
|
| 129 |
+
"rewards/rejected": -4.662972927093506,
|
| 130 |
+
"step": 70
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.02572347266881029,
|
| 134 |
+
"grad_norm": 360.4170837402344,
|
| 135 |
+
"learning_rate": 1.185e-05,
|
| 136 |
+
"logits/chosen": -2.468116044998169,
|
| 137 |
+
"logits/rejected": -2.431053638458252,
|
| 138 |
+
"logps/chosen": -329.6983947753906,
|
| 139 |
+
"logps/rejected": -322.09808349609375,
|
| 140 |
+
"loss": 0.3447,
|
| 141 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 142 |
+
"rewards/chosen": -2.501462936401367,
|
| 143 |
+
"rewards/margins": 3.868928909301758,
|
| 144 |
+
"rewards/rejected": -6.370392322540283,
|
| 145 |
+
"step": 80
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.028938906752411574,
|
| 149 |
+
"grad_norm": 135.08279418945312,
|
| 150 |
+
"learning_rate": 1.3350000000000001e-05,
|
| 151 |
+
"logits/chosen": -2.365429639816284,
|
| 152 |
+
"logits/rejected": -2.29831862449646,
|
| 153 |
+
"logps/chosen": -408.6314697265625,
|
| 154 |
+
"logps/rejected": -409.2450256347656,
|
| 155 |
+
"loss": 0.5737,
|
| 156 |
+
"rewards/accuracies": 0.848214328289032,
|
| 157 |
+
"rewards/chosen": -11.146495819091797,
|
| 158 |
+
"rewards/margins": 3.926030397415161,
|
| 159 |
+
"rewards/rejected": -15.072525024414062,
|
| 160 |
+
"step": 90
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.03215434083601286,
|
| 164 |
+
"grad_norm": 28.869873046875,
|
| 165 |
+
"learning_rate": 1.485e-05,
|
| 166 |
+
"logits/chosen": -2.3386080265045166,
|
| 167 |
+
"logits/rejected": -2.2970244884490967,
|
| 168 |
+
"logps/chosen": -345.72576904296875,
|
| 169 |
+
"logps/rejected": -358.2042236328125,
|
| 170 |
+
"loss": 0.3053,
|
| 171 |
+
"rewards/accuracies": 0.860714316368103,
|
| 172 |
+
"rewards/chosen": -4.066442489624023,
|
| 173 |
+
"rewards/margins": 5.298585891723633,
|
| 174 |
+
"rewards/rejected": -9.365028381347656,
|
| 175 |
+
"step": 100
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 0.03536977491961415,
|
| 179 |
+
"grad_norm": 26.5097599029541,
|
| 180 |
+
"learning_rate": 1.635e-05,
|
| 181 |
+
"logits/chosen": -2.358365535736084,
|
| 182 |
+
"logits/rejected": -2.2937300205230713,
|
| 183 |
+
"logps/chosen": -377.52276611328125,
|
| 184 |
+
"logps/rejected": -378.28839111328125,
|
| 185 |
+
"loss": 0.388,
|
| 186 |
+
"rewards/accuracies": 0.860714316368103,
|
| 187 |
+
"rewards/chosen": -6.647670745849609,
|
| 188 |
+
"rewards/margins": 5.24035120010376,
|
| 189 |
+
"rewards/rejected": -11.888021469116211,
|
| 190 |
+
"step": 110
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.03858520900321544,
|
| 194 |
+
"grad_norm": 39.25172805786133,
|
| 195 |
+
"learning_rate": 1.785e-05,
|
| 196 |
+
"logits/chosen": -2.4902865886688232,
|
| 197 |
+
"logits/rejected": -2.4236950874328613,
|
| 198 |
+
"logps/chosen": -326.519287109375,
|
| 199 |
+
"logps/rejected": -324.75091552734375,
|
| 200 |
+
"loss": 0.7375,
|
| 201 |
+
"rewards/accuracies": 0.8375000953674316,
|
| 202 |
+
"rewards/chosen": -3.107428550720215,
|
| 203 |
+
"rewards/margins": 3.825024366378784,
|
| 204 |
+
"rewards/rejected": -6.932452201843262,
|
| 205 |
+
"step": 120
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.04180064308681672,
|
| 209 |
+
"grad_norm": 49.65993118286133,
|
| 210 |
+
"learning_rate": 1.935e-05,
|
| 211 |
+
"logits/chosen": -2.6321167945861816,
|
| 212 |
+
"logits/rejected": -2.6001830101013184,
|
| 213 |
+
"logps/chosen": -331.8643798828125,
|
| 214 |
+
"logps/rejected": -332.07867431640625,
|
| 215 |
+
"loss": 0.3162,
|
| 216 |
+
"rewards/accuracies": 0.862500011920929,
|
| 217 |
+
"rewards/chosen": -3.3056838512420654,
|
| 218 |
+
"rewards/margins": 4.056153774261475,
|
| 219 |
+
"rewards/rejected": -7.361837863922119,
|
| 220 |
+
"step": 130
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.04501607717041801,
|
| 224 |
+
"grad_norm": 34.13883590698242,
|
| 225 |
+
"learning_rate": 2.085e-05,
|
| 226 |
+
"logits/chosen": -2.4387283325195312,
|
| 227 |
+
"logits/rejected": -2.3903980255126953,
|
| 228 |
+
"logps/chosen": -396.2072448730469,
|
| 229 |
+
"logps/rejected": -413.0238342285156,
|
| 230 |
+
"loss": 0.3161,
|
| 231 |
+
"rewards/accuracies": 0.887499988079071,
|
| 232 |
+
"rewards/chosen": -9.951654434204102,
|
| 233 |
+
"rewards/margins": 5.647161483764648,
|
| 234 |
+
"rewards/rejected": -15.59881591796875,
|
| 235 |
+
"step": 140
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.04823151125401929,
|
| 239 |
+
"grad_norm": 14.36856460571289,
|
| 240 |
+
"learning_rate": 2.235e-05,
|
| 241 |
+
"logits/chosen": -2.301513195037842,
|
| 242 |
+
"logits/rejected": -2.206355094909668,
|
| 243 |
+
"logps/chosen": -356.59088134765625,
|
| 244 |
+
"logps/rejected": -376.6296691894531,
|
| 245 |
+
"loss": 0.3143,
|
| 246 |
+
"rewards/accuracies": 0.8732143640518188,
|
| 247 |
+
"rewards/chosen": -6.92374324798584,
|
| 248 |
+
"rewards/margins": 5.8192524909973145,
|
| 249 |
+
"rewards/rejected": -12.742996215820312,
|
| 250 |
+
"step": 150
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.05144694533762058,
|
| 254 |
+
"grad_norm": 10.570508003234863,
|
| 255 |
+
"learning_rate": 2.385e-05,
|
| 256 |
+
"logits/chosen": -2.2517690658569336,
|
| 257 |
+
"logits/rejected": -2.222245693206787,
|
| 258 |
+
"logps/chosen": -386.21380615234375,
|
| 259 |
+
"logps/rejected": -392.8358459472656,
|
| 260 |
+
"loss": 0.3594,
|
| 261 |
+
"rewards/accuracies": 0.8285714983940125,
|
| 262 |
+
"rewards/chosen": -8.972579956054688,
|
| 263 |
+
"rewards/margins": 4.516054153442383,
|
| 264 |
+
"rewards/rejected": -13.488635063171387,
|
| 265 |
+
"step": 160
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.05466237942122187,
|
| 269 |
+
"grad_norm": 18.00568389892578,
|
| 270 |
+
"learning_rate": 2.535e-05,
|
| 271 |
+
"logits/chosen": -2.4203078746795654,
|
| 272 |
+
"logits/rejected": -2.3945605754852295,
|
| 273 |
+
"logps/chosen": -387.5201416015625,
|
| 274 |
+
"logps/rejected": -392.7701110839844,
|
| 275 |
+
"loss": 0.3523,
|
| 276 |
+
"rewards/accuracies": 0.848214328289032,
|
| 277 |
+
"rewards/chosen": -8.321182250976562,
|
| 278 |
+
"rewards/margins": 4.6146345138549805,
|
| 279 |
+
"rewards/rejected": -12.935816764831543,
|
| 280 |
+
"step": 170
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.05787781350482315,
|
| 284 |
+
"grad_norm": 11.757823944091797,
|
| 285 |
+
"learning_rate": 2.6850000000000002e-05,
|
| 286 |
+
"logits/chosen": -2.5331153869628906,
|
| 287 |
+
"logits/rejected": -2.4912378787994385,
|
| 288 |
+
"logps/chosen": -406.7548828125,
|
| 289 |
+
"logps/rejected": -418.08673095703125,
|
| 290 |
+
"loss": 0.3379,
|
| 291 |
+
"rewards/accuracies": 0.8625000715255737,
|
| 292 |
+
"rewards/chosen": -9.600198745727539,
|
| 293 |
+
"rewards/margins": 5.207104682922363,
|
| 294 |
+
"rewards/rejected": -14.807302474975586,
|
| 295 |
+
"step": 180
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.06109324758842444,
|
| 299 |
+
"grad_norm": 7.302403926849365,
|
| 300 |
+
"learning_rate": 2.8349999999999998e-05,
|
| 301 |
+
"logits/chosen": -2.309605836868286,
|
| 302 |
+
"logits/rejected": -2.2778573036193848,
|
| 303 |
+
"logps/chosen": -405.32122802734375,
|
| 304 |
+
"logps/rejected": -420.27557373046875,
|
| 305 |
+
"loss": 0.3828,
|
| 306 |
+
"rewards/accuracies": 0.8660715222358704,
|
| 307 |
+
"rewards/chosen": -9.99227523803711,
|
| 308 |
+
"rewards/margins": 6.3076934814453125,
|
| 309 |
+
"rewards/rejected": -16.299968719482422,
|
| 310 |
+
"step": 190
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.06430868167202572,
|
| 314 |
+
"grad_norm": 11.398672103881836,
|
| 315 |
+
"learning_rate": 2.985e-05,
|
| 316 |
+
"logits/chosen": -2.569981336593628,
|
| 317 |
+
"logits/rejected": -2.526599168777466,
|
| 318 |
+
"logps/chosen": -461.9549865722656,
|
| 319 |
+
"logps/rejected": -473.1504821777344,
|
| 320 |
+
"loss": 0.3788,
|
| 321 |
+
"rewards/accuracies": 0.8553571701049805,
|
| 322 |
+
"rewards/chosen": -15.653833389282227,
|
| 323 |
+
"rewards/margins": 6.788999080657959,
|
| 324 |
+
"rewards/rejected": -22.442832946777344,
|
| 325 |
+
"step": 200
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.06752411575562701,
|
| 329 |
+
"grad_norm": 50.62058639526367,
|
| 330 |
+
"learning_rate": 2.9963499997375575e-05,
|
| 331 |
+
"logits/chosen": -2.417654514312744,
|
| 332 |
+
"logits/rejected": -2.3606505393981934,
|
| 333 |
+
"logps/chosen": -482.07659912109375,
|
| 334 |
+
"logps/rejected": -515.6975708007812,
|
| 335 |
+
"loss": 0.4418,
|
| 336 |
+
"rewards/accuracies": 0.8785713911056519,
|
| 337 |
+
"rewards/chosen": -17.540700912475586,
|
| 338 |
+
"rewards/margins": 8.336698532104492,
|
| 339 |
+
"rewards/rejected": -25.87740135192871,
|
| 340 |
+
"step": 210
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.0707395498392283,
|
| 344 |
+
"grad_norm": 16.234468460083008,
|
| 345 |
+
"learning_rate": 2.9837652906305957e-05,
|
| 346 |
+
"logits/chosen": -2.5475172996520996,
|
| 347 |
+
"logits/rejected": -2.495272159576416,
|
| 348 |
+
"logps/chosen": -479.1644592285156,
|
| 349 |
+
"logps/rejected": -494.456298828125,
|
| 350 |
+
"loss": 0.5664,
|
| 351 |
+
"rewards/accuracies": 0.8053572773933411,
|
| 352 |
+
"rewards/chosen": -17.714771270751953,
|
| 353 |
+
"rewards/margins": 5.708583831787109,
|
| 354 |
+
"rewards/rejected": -23.42335319519043,
|
| 355 |
+
"step": 220
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.07395498392282958,
|
| 359 |
+
"grad_norm": 14.656303405761719,
|
| 360 |
+
"learning_rate": 2.9623087873611065e-05,
|
| 361 |
+
"logits/chosen": -2.502220630645752,
|
| 362 |
+
"logits/rejected": -2.480044364929199,
|
| 363 |
+
"logps/chosen": -408.70941162109375,
|
| 364 |
+
"logps/rejected": -429.931640625,
|
| 365 |
+
"loss": 0.3782,
|
| 366 |
+
"rewards/accuracies": 0.8428570628166199,
|
| 367 |
+
"rewards/chosen": -10.620994567871094,
|
| 368 |
+
"rewards/margins": 5.9877166748046875,
|
| 369 |
+
"rewards/rejected": -16.60871124267578,
|
| 370 |
+
"step": 230
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.07717041800643087,
|
| 374 |
+
"grad_norm": 10.515886306762695,
|
| 375 |
+
"learning_rate": 2.932164630064359e-05,
|
| 376 |
+
"logits/chosen": -2.1353824138641357,
|
| 377 |
+
"logits/rejected": -2.071852445602417,
|
| 378 |
+
"logps/chosen": -424.79046630859375,
|
| 379 |
+
"logps/rejected": -435.5794372558594,
|
| 380 |
+
"loss": 0.4634,
|
| 381 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 382 |
+
"rewards/chosen": -12.948244094848633,
|
| 383 |
+
"rewards/margins": 5.95263671875,
|
| 384 |
+
"rewards/rejected": -18.90087890625,
|
| 385 |
+
"step": 240
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.08038585209003216,
|
| 389 |
+
"grad_norm": 13.274107933044434,
|
| 390 |
+
"learning_rate": 2.8935915164942478e-05,
|
| 391 |
+
"logits/chosen": -2.3533787727355957,
|
| 392 |
+
"logits/rejected": -2.30831241607666,
|
| 393 |
+
"logps/chosen": -433.0838928222656,
|
| 394 |
+
"logps/rejected": -477.1802673339844,
|
| 395 |
+
"loss": 0.4355,
|
| 396 |
+
"rewards/accuracies": 0.860714316368103,
|
| 397 |
+
"rewards/chosen": -15.225809097290039,
|
| 398 |
+
"rewards/margins": 7.938222408294678,
|
| 399 |
+
"rewards/rejected": -23.164031982421875,
|
| 400 |
+
"step": 250
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.08360128617363344,
|
| 404 |
+
"grad_norm": 9.96252155303955,
|
| 405 |
+
"learning_rate": 2.846920481874051e-05,
|
| 406 |
+
"logits/chosen": -2.216628074645996,
|
| 407 |
+
"logits/rejected": -2.1560254096984863,
|
| 408 |
+
"logps/chosen": -403.18548583984375,
|
| 409 |
+
"logps/rejected": -416.61419677734375,
|
| 410 |
+
"loss": 0.4278,
|
| 411 |
+
"rewards/accuracies": 0.8517857789993286,
|
| 412 |
+
"rewards/chosen": -10.419198036193848,
|
| 413 |
+
"rewards/margins": 6.329415798187256,
|
| 414 |
+
"rewards/rejected": -16.748613357543945,
|
| 415 |
+
"step": 260
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.08681672025723473,
|
| 419 |
+
"grad_norm": 28.472272872924805,
|
| 420 |
+
"learning_rate": 2.7925520579456026e-05,
|
| 421 |
+
"logits/chosen": -2.186771869659424,
|
| 422 |
+
"logits/rejected": -2.1579926013946533,
|
| 423 |
+
"logps/chosen": -373.64166259765625,
|
| 424 |
+
"logps/rejected": -395.2644348144531,
|
| 425 |
+
"loss": 0.396,
|
| 426 |
+
"rewards/accuracies": 0.8625000715255737,
|
| 427 |
+
"rewards/chosen": -8.484575271606445,
|
| 428 |
+
"rewards/margins": 6.288187026977539,
|
| 429 |
+
"rewards/rejected": -14.772761344909668,
|
| 430 |
+
"step": 270
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.09003215434083602,
|
| 434 |
+
"grad_norm": 19.81985092163086,
|
| 435 |
+
"learning_rate": 2.7309528355979613e-05,
|
| 436 |
+
"logits/chosen": -2.288975238800049,
|
| 437 |
+
"logits/rejected": -2.287881374359131,
|
| 438 |
+
"logps/chosen": -481.0345764160156,
|
| 439 |
+
"logps/rejected": -474.57958984375,
|
| 440 |
+
"loss": 1.6168,
|
| 441 |
+
"rewards/accuracies": 0.7214285135269165,
|
| 442 |
+
"rewards/chosen": -17.42532730102539,
|
| 443 |
+
"rewards/margins": 4.1218461990356445,
|
| 444 |
+
"rewards/rejected": -21.547168731689453,
|
| 445 |
+
"step": 280
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.0932475884244373,
|
| 449 |
+
"grad_norm": 11.689517974853516,
|
| 450 |
+
"learning_rate": 2.6626514605751792e-05,
|
| 451 |
+
"logits/chosen": -2.0175223350524902,
|
| 452 |
+
"logits/rejected": -1.9642770290374756,
|
| 453 |
+
"logps/chosen": -470.8360290527344,
|
| 454 |
+
"logps/rejected": -516.0283203125,
|
| 455 |
+
"loss": 0.3033,
|
| 456 |
+
"rewards/accuracies": 0.8696429133415222,
|
| 457 |
+
"rewards/chosen": -17.717975616455078,
|
| 458 |
+
"rewards/margins": 9.43533992767334,
|
| 459 |
+
"rewards/rejected": -27.153316497802734,
|
| 460 |
+
"step": 290
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.09646302250803858,
|
| 464 |
+
"grad_norm": 10.816216468811035,
|
| 465 |
+
"learning_rate": 2.5882340966280716e-05,
|
| 466 |
+
"logits/chosen": -2.333395481109619,
|
| 467 |
+
"logits/rejected": -2.308253049850464,
|
| 468 |
+
"logps/chosen": -496.63201904296875,
|
| 469 |
+
"logps/rejected": -514.8468017578125,
|
| 470 |
+
"loss": 0.5552,
|
| 471 |
+
"rewards/accuracies": 0.848214328289032,
|
| 472 |
+
"rewards/chosen": -20.267597198486328,
|
| 473 |
+
"rewards/margins": 6.434575080871582,
|
| 474 |
+
"rewards/rejected": -26.702173233032227,
|
| 475 |
+
"step": 300
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 0.09967845659163987,
|
| 479 |
+
"grad_norm": 9.920787811279297,
|
| 480 |
+
"learning_rate": 2.508339395045323e-05,
|
| 481 |
+
"logits/chosen": -2.5437283515930176,
|
| 482 |
+
"logits/rejected": -2.5304923057556152,
|
| 483 |
+
"logps/chosen": -490.4562072753906,
|
| 484 |
+
"logps/rejected": -504.1741638183594,
|
| 485 |
+
"loss": 0.332,
|
| 486 |
+
"rewards/accuracies": 0.8642856478691101,
|
| 487 |
+
"rewards/chosen": -19.00229835510254,
|
| 488 |
+
"rewards/margins": 6.146671295166016,
|
| 489 |
+
"rewards/rejected": -25.148969650268555,
|
| 490 |
+
"step": 310
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.10289389067524116,
|
| 494 |
+
"grad_norm": 19.131654739379883,
|
| 495 |
+
"learning_rate": 2.4236530137354944e-05,
|
| 496 |
+
"logits/chosen": -2.2978572845458984,
|
| 497 |
+
"logits/rejected": -2.2660460472106934,
|
| 498 |
+
"logps/chosen": -493.71429443359375,
|
| 499 |
+
"logps/rejected": -541.1251831054688,
|
| 500 |
+
"loss": 0.307,
|
| 501 |
+
"rewards/accuracies": 0.8767857551574707,
|
| 502 |
+
"rewards/chosen": -19.497310638427734,
|
| 503 |
+
"rewards/margins": 8.083097457885742,
|
| 504 |
+
"rewards/rejected": -27.580408096313477,
|
| 505 |
+
"step": 320
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.10610932475884244,
|
| 509 |
+
"grad_norm": 20.32062339782715,
|
| 510 |
+
"learning_rate": 2.3349017328973037e-05,
|
| 511 |
+
"logits/chosen": -2.4487316608428955,
|
| 512 |
+
"logits/rejected": -2.4205942153930664,
|
| 513 |
+
"logps/chosen": -448.8963317871094,
|
| 514 |
+
"logps/rejected": -494.49176025390625,
|
| 515 |
+
"loss": 0.3706,
|
| 516 |
+
"rewards/accuracies": 0.8642857670783997,
|
| 517 |
+
"rewards/chosen": -15.035717964172363,
|
| 518 |
+
"rewards/margins": 8.205968856811523,
|
| 519 |
+
"rewards/rejected": -23.24168586730957,
|
| 520 |
+
"step": 330
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.10932475884244373,
|
| 524 |
+
"grad_norm": 13.464560508728027,
|
| 525 |
+
"learning_rate": 2.2428472177775835e-05,
|
| 526 |
+
"logits/chosen": -2.5762939453125,
|
| 527 |
+
"logits/rejected": -2.534386157989502,
|
| 528 |
+
"logps/chosen": -456.61859130859375,
|
| 529 |
+
"logps/rejected": -477.6875915527344,
|
| 530 |
+
"loss": 0.3679,
|
| 531 |
+
"rewards/accuracies": 0.8625000715255737,
|
| 532 |
+
"rewards/chosen": -16.53495979309082,
|
| 533 |
+
"rewards/margins": 6.909937858581543,
|
| 534 |
+
"rewards/rejected": -23.444900512695312,
|
| 535 |
+
"step": 340
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.11254019292604502,
|
| 539 |
+
"grad_norm": 14.568502426147461,
|
| 540 |
+
"learning_rate": 2.1482794820450814e-05,
|
| 541 |
+
"logits/chosen": -2.5605056285858154,
|
| 542 |
+
"logits/rejected": -2.5096778869628906,
|
| 543 |
+
"logps/chosen": -423.26300048828125,
|
| 544 |
+
"logps/rejected": -447.6953125,
|
| 545 |
+
"loss": 0.342,
|
| 546 |
+
"rewards/accuracies": 0.8732143640518188,
|
| 547 |
+
"rewards/chosen": -12.514073371887207,
|
| 548 |
+
"rewards/margins": 7.575278282165527,
|
| 549 |
+
"rewards/rejected": -20.089353561401367,
|
| 550 |
+
"step": 350
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.1157556270096463,
|
| 554 |
+
"grad_norm": 9.758018493652344,
|
| 555 |
+
"learning_rate": 2.05201010787753e-05,
|
| 556 |
+
"logits/chosen": -2.1697499752044678,
|
| 557 |
+
"logits/rejected": -2.1387410163879395,
|
| 558 |
+
"logps/chosen": -456.02984619140625,
|
| 559 |
+
"logps/rejected": -503.065185546875,
|
| 560 |
+
"loss": 0.2779,
|
| 561 |
+
"rewards/accuracies": 0.889285683631897,
|
| 562 |
+
"rewards/chosen": -16.698528289794922,
|
| 563 |
+
"rewards/margins": 9.026225090026855,
|
| 564 |
+
"rewards/rejected": -25.72475242614746,
|
| 565 |
+
"step": 360
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 0.1189710610932476,
|
| 569 |
+
"grad_norm": 18.256454467773438,
|
| 570 |
+
"learning_rate": 1.9548652809473558e-05,
|
| 571 |
+
"logits/chosen": -2.046221971511841,
|
| 572 |
+
"logits/rejected": -2.0130884647369385,
|
| 573 |
+
"logps/chosen": -491.8714904785156,
|
| 574 |
+
"logps/rejected": -533.032958984375,
|
| 575 |
+
"loss": 0.3466,
|
| 576 |
+
"rewards/accuracies": 0.8571429252624512,
|
| 577 |
+
"rewards/chosen": -19.596403121948242,
|
| 578 |
+
"rewards/margins": 8.155044555664062,
|
| 579 |
+
"rewards/rejected": -27.751449584960938,
|
| 580 |
+
"step": 370
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.12218649517684887,
|
| 584 |
+
"grad_norm": 12.129895210266113,
|
| 585 |
+
"learning_rate": 1.8576787000799002e-05,
|
| 586 |
+
"logits/chosen": -2.4258432388305664,
|
| 587 |
+
"logits/rejected": -2.3579177856445312,
|
| 588 |
+
"logps/chosen": -492.90826416015625,
|
| 589 |
+
"logps/rejected": -544.7718505859375,
|
| 590 |
+
"loss": 0.2529,
|
| 591 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 592 |
+
"rewards/chosen": -20.450740814208984,
|
| 593 |
+
"rewards/margins": 9.103205680847168,
|
| 594 |
+
"rewards/rejected": -29.553945541381836,
|
| 595 |
+
"step": 380
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 0.12540192926045016,
|
| 599 |
+
"grad_norm": 46.050537109375,
|
| 600 |
+
"learning_rate": 1.7612844224336228e-05,
|
| 601 |
+
"logits/chosen": -2.5398786067962646,
|
| 602 |
+
"logits/rejected": -2.515723705291748,
|
| 603 |
+
"logps/chosen": -559.4112548828125,
|
| 604 |
+
"logps/rejected": -574.40234375,
|
| 605 |
+
"loss": 0.3799,
|
| 606 |
+
"rewards/accuracies": 0.8642857670783997,
|
| 607 |
+
"rewards/chosen": -25.749526977539062,
|
| 608 |
+
"rewards/margins": 6.102494716644287,
|
| 609 |
+
"rewards/rejected": -31.852020263671875,
|
| 610 |
+
"step": 390
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.12861736334405144,
|
| 614 |
+
"grad_norm": 21.291101455688477,
|
| 615 |
+
"learning_rate": 1.666509705605072e-05,
|
| 616 |
+
"logits/chosen": -2.3730740547180176,
|
| 617 |
+
"logits/rejected": -2.329524040222168,
|
| 618 |
+
"logps/chosen": -522.7748413085938,
|
| 619 |
+
"logps/rejected": -569.830322265625,
|
| 620 |
+
"loss": 0.3555,
|
| 621 |
+
"rewards/accuracies": 0.8660714030265808,
|
| 622 |
+
"rewards/chosen": -21.334875106811523,
|
| 623 |
+
"rewards/margins": 9.661813735961914,
|
| 624 |
+
"rewards/rejected": -30.996685028076172,
|
| 625 |
+
"step": 400
|
| 626 |
+
}
|
| 627 |
+
],
|
| 628 |
+
"logging_steps": 10,
|
| 629 |
+
"max_steps": 539,
|
| 630 |
+
"num_input_tokens_seen": 0,
|
| 631 |
+
"num_train_epochs": 1,
|
| 632 |
+
"save_steps": 100,
|
| 633 |
+
"stateful_callbacks": {
|
| 634 |
+
"TrainerControl": {
|
| 635 |
+
"args": {
|
| 636 |
+
"should_epoch_stop": false,
|
| 637 |
+
"should_evaluate": false,
|
| 638 |
+
"should_log": false,
|
| 639 |
+
"should_save": true,
|
| 640 |
+
"should_training_stop": false
|
| 641 |
+
},
|
| 642 |
+
"attributes": {}
|
| 643 |
+
}
|
| 644 |
+
},
|
| 645 |
+
"total_flos": 0.0,
|
| 646 |
+
"train_batch_size": 28,
|
| 647 |
+
"trial_name": null,
|
| 648 |
+
"trial_params": null
|
| 649 |
+
}
|
checkpoint-400/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa2d510c9f10ad6f48833d1edc591cf4149503b20d3fc84afc920182e0b6bd6e
|
| 3 |
+
size 8593
|
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MistralForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"head_dim": null,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 14336,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"model_type": "mistral",
|
| 15 |
+
"num_attention_heads": 32,
|
| 16 |
+
"num_hidden_layers": 32,
|
| 17 |
+
"num_key_value_heads": 8,
|
| 18 |
+
"rms_norm_eps": 1e-05,
|
| 19 |
+
"rope_theta": 10000.0,
|
| 20 |
+
"sliding_window": 4096,
|
| 21 |
+
"tie_word_embeddings": false,
|
| 22 |
+
"torch_dtype": "bfloat16",
|
| 23 |
+
"transformers_version": "4.55.0",
|
| 24 |
+
"use_cache": false,
|
| 25 |
+
"vocab_size": 32002
|
| 26 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"transformers_version": "4.55.0"
|
| 7 |
+
}
|
model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43fb9f6ea6d83c0dcfe4bd6cc29e40c9a36f1f8d11df666d6cf735944c72d7c8
|
| 3 |
+
size 4936382264
|
model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78ff9c67b39e07fdd7ab392b5a9298ab9fa787a44c6834e237f3968c074755a7
|
| 3 |
+
size 4913839000
|
model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0b9a0a4bbb5a42f09c685c21500ca0084dda9a09493fc640d397434f4655665
|
| 3 |
+
size 4968912088
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,747 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 7325634560,
|
| 4 |
+
"total_size": 14819041280
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 11 |
+
"model.layers.0.mlp.down_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 12 |
+
"model.layers.0.mlp.down_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 13 |
+
"model.layers.0.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 14 |
+
"model.layers.0.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 15 |
+
"model.layers.0.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"model.layers.0.mlp.up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 17 |
+
"model.layers.0.mlp.up_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 18 |
+
"model.layers.0.mlp.up_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 19 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 21 |
+
"model.layers.0.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 22 |
+
"model.layers.0.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 23 |
+
"model.layers.0.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 24 |
+
"model.layers.0.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 25 |
+
"model.layers.0.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 26 |
+
"model.layers.0.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 27 |
+
"model.layers.0.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 28 |
+
"model.layers.0.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 29 |
+
"model.layers.0.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 30 |
+
"model.layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 31 |
+
"model.layers.0.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 32 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 33 |
+
"model.layers.1.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 34 |
+
"model.layers.1.mlp.down_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 35 |
+
"model.layers.1.mlp.down_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 36 |
+
"model.layers.1.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 37 |
+
"model.layers.1.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 38 |
+
"model.layers.1.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 39 |
+
"model.layers.1.mlp.up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 40 |
+
"model.layers.1.mlp.up_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 41 |
+
"model.layers.1.mlp.up_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 42 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 43 |
+
"model.layers.1.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 44 |
+
"model.layers.1.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 45 |
+
"model.layers.1.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 46 |
+
"model.layers.1.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 47 |
+
"model.layers.1.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 48 |
+
"model.layers.1.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 49 |
+
"model.layers.1.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 50 |
+
"model.layers.1.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 51 |
+
"model.layers.1.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 52 |
+
"model.layers.1.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 53 |
+
"model.layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 54 |
+
"model.layers.1.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 55 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 56 |
+
"model.layers.10.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 57 |
+
"model.layers.10.mlp.down_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"model.layers.10.mlp.down_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 59 |
+
"model.layers.10.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 60 |
+
"model.layers.10.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 61 |
+
"model.layers.10.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 62 |
+
"model.layers.10.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 63 |
+
"model.layers.10.mlp.up_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 64 |
+
"model.layers.10.mlp.up_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 65 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 66 |
+
"model.layers.10.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 67 |
+
"model.layers.10.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 68 |
+
"model.layers.10.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 69 |
+
"model.layers.10.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 70 |
+
"model.layers.10.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 71 |
+
"model.layers.10.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 72 |
+
"model.layers.10.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 73 |
+
"model.layers.10.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 74 |
+
"model.layers.10.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 75 |
+
"model.layers.10.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 76 |
+
"model.layers.10.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 77 |
+
"model.layers.10.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 78 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 79 |
+
"model.layers.11.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 80 |
+
"model.layers.11.mlp.down_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 81 |
+
"model.layers.11.mlp.down_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"model.layers.11.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 83 |
+
"model.layers.11.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"model.layers.11.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.layers.11.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.layers.11.mlp.up_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.layers.11.mlp.up_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 89 |
+
"model.layers.11.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 90 |
+
"model.layers.11.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 91 |
+
"model.layers.11.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 92 |
+
"model.layers.11.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 93 |
+
"model.layers.11.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 94 |
+
"model.layers.11.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 95 |
+
"model.layers.11.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 96 |
+
"model.layers.11.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 97 |
+
"model.layers.11.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 98 |
+
"model.layers.11.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 99 |
+
"model.layers.11.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 100 |
+
"model.layers.11.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 101 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 102 |
+
"model.layers.12.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.layers.12.mlp.down_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.layers.12.mlp.down_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.layers.12.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.layers.12.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.layers.12.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.layers.12.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.layers.12.mlp.up_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.layers.12.mlp.up_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.layers.12.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 113 |
+
"model.layers.12.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 114 |
+
"model.layers.12.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 115 |
+
"model.layers.12.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 116 |
+
"model.layers.12.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 117 |
+
"model.layers.12.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 118 |
+
"model.layers.12.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 119 |
+
"model.layers.12.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 120 |
+
"model.layers.12.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 121 |
+
"model.layers.12.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 122 |
+
"model.layers.12.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 123 |
+
"model.layers.12.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 124 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 125 |
+
"model.layers.13.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 126 |
+
"model.layers.13.mlp.down_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 127 |
+
"model.layers.13.mlp.down_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 128 |
+
"model.layers.13.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 129 |
+
"model.layers.13.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 130 |
+
"model.layers.13.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 131 |
+
"model.layers.13.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 132 |
+
"model.layers.13.mlp.up_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 133 |
+
"model.layers.13.mlp.up_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 134 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 135 |
+
"model.layers.13.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 136 |
+
"model.layers.13.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 137 |
+
"model.layers.13.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 138 |
+
"model.layers.13.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 139 |
+
"model.layers.13.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 140 |
+
"model.layers.13.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 141 |
+
"model.layers.13.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 142 |
+
"model.layers.13.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 143 |
+
"model.layers.13.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 144 |
+
"model.layers.13.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 145 |
+
"model.layers.13.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 146 |
+
"model.layers.13.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 147 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 148 |
+
"model.layers.14.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 149 |
+
"model.layers.14.mlp.down_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 150 |
+
"model.layers.14.mlp.down_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 151 |
+
"model.layers.14.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 152 |
+
"model.layers.14.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 153 |
+
"model.layers.14.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 154 |
+
"model.layers.14.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 155 |
+
"model.layers.14.mlp.up_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 156 |
+
"model.layers.14.mlp.up_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 157 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 158 |
+
"model.layers.14.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 159 |
+
"model.layers.14.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 160 |
+
"model.layers.14.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 161 |
+
"model.layers.14.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 162 |
+
"model.layers.14.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 163 |
+
"model.layers.14.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 164 |
+
"model.layers.14.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 165 |
+
"model.layers.14.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 166 |
+
"model.layers.14.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 167 |
+
"model.layers.14.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 168 |
+
"model.layers.14.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 169 |
+
"model.layers.14.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 170 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 171 |
+
"model.layers.15.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 172 |
+
"model.layers.15.mlp.down_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 173 |
+
"model.layers.15.mlp.down_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 174 |
+
"model.layers.15.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 175 |
+
"model.layers.15.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 176 |
+
"model.layers.15.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 177 |
+
"model.layers.15.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 178 |
+
"model.layers.15.mlp.up_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 179 |
+
"model.layers.15.mlp.up_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 180 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 181 |
+
"model.layers.15.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 182 |
+
"model.layers.15.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 183 |
+
"model.layers.15.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 184 |
+
"model.layers.15.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 185 |
+
"model.layers.15.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 186 |
+
"model.layers.15.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 187 |
+
"model.layers.15.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 188 |
+
"model.layers.15.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 189 |
+
"model.layers.15.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 190 |
+
"model.layers.15.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 191 |
+
"model.layers.15.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 192 |
+
"model.layers.15.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 193 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 194 |
+
"model.layers.16.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 195 |
+
"model.layers.16.mlp.down_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 196 |
+
"model.layers.16.mlp.down_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 197 |
+
"model.layers.16.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 198 |
+
"model.layers.16.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 199 |
+
"model.layers.16.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 200 |
+
"model.layers.16.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 201 |
+
"model.layers.16.mlp.up_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 202 |
+
"model.layers.16.mlp.up_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 203 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 204 |
+
"model.layers.16.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 205 |
+
"model.layers.16.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 206 |
+
"model.layers.16.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 207 |
+
"model.layers.16.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 208 |
+
"model.layers.16.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 209 |
+
"model.layers.16.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 210 |
+
"model.layers.16.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 211 |
+
"model.layers.16.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 212 |
+
"model.layers.16.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 213 |
+
"model.layers.16.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 214 |
+
"model.layers.16.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 215 |
+
"model.layers.16.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 216 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 217 |
+
"model.layers.17.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 218 |
+
"model.layers.17.mlp.down_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 219 |
+
"model.layers.17.mlp.down_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 220 |
+
"model.layers.17.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 221 |
+
"model.layers.17.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 222 |
+
"model.layers.17.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 223 |
+
"model.layers.17.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 224 |
+
"model.layers.17.mlp.up_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 225 |
+
"model.layers.17.mlp.up_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 226 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 227 |
+
"model.layers.17.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 228 |
+
"model.layers.17.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 229 |
+
"model.layers.17.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 230 |
+
"model.layers.17.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 231 |
+
"model.layers.17.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 232 |
+
"model.layers.17.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 233 |
+
"model.layers.17.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 234 |
+
"model.layers.17.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 235 |
+
"model.layers.17.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 236 |
+
"model.layers.17.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 237 |
+
"model.layers.17.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 238 |
+
"model.layers.17.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 239 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 240 |
+
"model.layers.18.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 241 |
+
"model.layers.18.mlp.down_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 242 |
+
"model.layers.18.mlp.down_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 243 |
+
"model.layers.18.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 244 |
+
"model.layers.18.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 245 |
+
"model.layers.18.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 246 |
+
"model.layers.18.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 247 |
+
"model.layers.18.mlp.up_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 248 |
+
"model.layers.18.mlp.up_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 249 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 250 |
+
"model.layers.18.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 251 |
+
"model.layers.18.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 252 |
+
"model.layers.18.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 253 |
+
"model.layers.18.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 254 |
+
"model.layers.18.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 255 |
+
"model.layers.18.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 256 |
+
"model.layers.18.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 257 |
+
"model.layers.18.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 258 |
+
"model.layers.18.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 259 |
+
"model.layers.18.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 260 |
+
"model.layers.18.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 261 |
+
"model.layers.18.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 262 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 263 |
+
"model.layers.19.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 264 |
+
"model.layers.19.mlp.down_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 265 |
+
"model.layers.19.mlp.down_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 266 |
+
"model.layers.19.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 267 |
+
"model.layers.19.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 268 |
+
"model.layers.19.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 269 |
+
"model.layers.19.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 270 |
+
"model.layers.19.mlp.up_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 271 |
+
"model.layers.19.mlp.up_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 272 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 273 |
+
"model.layers.19.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 274 |
+
"model.layers.19.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 275 |
+
"model.layers.19.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 276 |
+
"model.layers.19.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 277 |
+
"model.layers.19.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 278 |
+
"model.layers.19.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 279 |
+
"model.layers.19.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 280 |
+
"model.layers.19.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 281 |
+
"model.layers.19.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 282 |
+
"model.layers.19.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 283 |
+
"model.layers.19.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 284 |
+
"model.layers.19.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 285 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 286 |
+
"model.layers.2.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 287 |
+
"model.layers.2.mlp.down_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 288 |
+
"model.layers.2.mlp.down_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 289 |
+
"model.layers.2.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 290 |
+
"model.layers.2.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 291 |
+
"model.layers.2.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 292 |
+
"model.layers.2.mlp.up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 293 |
+
"model.layers.2.mlp.up_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 294 |
+
"model.layers.2.mlp.up_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 295 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 296 |
+
"model.layers.2.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 297 |
+
"model.layers.2.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 298 |
+
"model.layers.2.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 299 |
+
"model.layers.2.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 300 |
+
"model.layers.2.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 301 |
+
"model.layers.2.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 302 |
+
"model.layers.2.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 303 |
+
"model.layers.2.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 304 |
+
"model.layers.2.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 305 |
+
"model.layers.2.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 306 |
+
"model.layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 307 |
+
"model.layers.2.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 308 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 309 |
+
"model.layers.20.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 310 |
+
"model.layers.20.mlp.down_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 311 |
+
"model.layers.20.mlp.down_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 312 |
+
"model.layers.20.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 313 |
+
"model.layers.20.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 314 |
+
"model.layers.20.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 315 |
+
"model.layers.20.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 316 |
+
"model.layers.20.mlp.up_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 317 |
+
"model.layers.20.mlp.up_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 318 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 319 |
+
"model.layers.20.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 320 |
+
"model.layers.20.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 321 |
+
"model.layers.20.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 322 |
+
"model.layers.20.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 323 |
+
"model.layers.20.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 324 |
+
"model.layers.20.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 325 |
+
"model.layers.20.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 326 |
+
"model.layers.20.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 327 |
+
"model.layers.20.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 328 |
+
"model.layers.20.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 329 |
+
"model.layers.20.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 330 |
+
"model.layers.20.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 331 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 332 |
+
"model.layers.21.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 333 |
+
"model.layers.21.mlp.down_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 334 |
+
"model.layers.21.mlp.down_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 335 |
+
"model.layers.21.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 336 |
+
"model.layers.21.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 337 |
+
"model.layers.21.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 338 |
+
"model.layers.21.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 339 |
+
"model.layers.21.mlp.up_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 340 |
+
"model.layers.21.mlp.up_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 341 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 342 |
+
"model.layers.21.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 343 |
+
"model.layers.21.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 344 |
+
"model.layers.21.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 345 |
+
"model.layers.21.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 346 |
+
"model.layers.21.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 347 |
+
"model.layers.21.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 348 |
+
"model.layers.21.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 349 |
+
"model.layers.21.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 350 |
+
"model.layers.21.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 351 |
+
"model.layers.21.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
|
| 352 |
+
"model.layers.21.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
|
| 353 |
+
"model.layers.21.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
|
| 354 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 355 |
+
"model.layers.22.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 356 |
+
"model.layers.22.mlp.down_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 357 |
+
"model.layers.22.mlp.down_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 358 |
+
"model.layers.22.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 359 |
+
"model.layers.22.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 360 |
+
"model.layers.22.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 361 |
+
"model.layers.22.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 362 |
+
"model.layers.22.mlp.up_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 363 |
+
"model.layers.22.mlp.up_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 364 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 365 |
+
"model.layers.22.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 366 |
+
"model.layers.22.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 367 |
+
"model.layers.22.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 368 |
+
"model.layers.22.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 369 |
+
"model.layers.22.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 370 |
+
"model.layers.22.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 371 |
+
"model.layers.22.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 372 |
+
"model.layers.22.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 373 |
+
"model.layers.22.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 374 |
+
"model.layers.22.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 375 |
+
"model.layers.22.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 376 |
+
"model.layers.22.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 377 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 378 |
+
"model.layers.23.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 379 |
+
"model.layers.23.mlp.down_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 380 |
+
"model.layers.23.mlp.down_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 381 |
+
"model.layers.23.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 382 |
+
"model.layers.23.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 383 |
+
"model.layers.23.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 384 |
+
"model.layers.23.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 385 |
+
"model.layers.23.mlp.up_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 386 |
+
"model.layers.23.mlp.up_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 387 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 388 |
+
"model.layers.23.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 389 |
+
"model.layers.23.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 390 |
+
"model.layers.23.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 391 |
+
"model.layers.23.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 392 |
+
"model.layers.23.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 393 |
+
"model.layers.23.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 394 |
+
"model.layers.23.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 395 |
+
"model.layers.23.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 396 |
+
"model.layers.23.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 397 |
+
"model.layers.23.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 398 |
+
"model.layers.23.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 399 |
+
"model.layers.23.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 400 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 401 |
+
"model.layers.24.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 402 |
+
"model.layers.24.mlp.down_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 403 |
+
"model.layers.24.mlp.down_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 404 |
+
"model.layers.24.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 405 |
+
"model.layers.24.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 406 |
+
"model.layers.24.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 407 |
+
"model.layers.24.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 408 |
+
"model.layers.24.mlp.up_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 409 |
+
"model.layers.24.mlp.up_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 410 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 411 |
+
"model.layers.24.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 412 |
+
"model.layers.24.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 413 |
+
"model.layers.24.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 414 |
+
"model.layers.24.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 415 |
+
"model.layers.24.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 416 |
+
"model.layers.24.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 417 |
+
"model.layers.24.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 418 |
+
"model.layers.24.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 419 |
+
"model.layers.24.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 420 |
+
"model.layers.24.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 421 |
+
"model.layers.24.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 422 |
+
"model.layers.24.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 423 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 424 |
+
"model.layers.25.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 425 |
+
"model.layers.25.mlp.down_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 426 |
+
"model.layers.25.mlp.down_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 427 |
+
"model.layers.25.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 428 |
+
"model.layers.25.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 429 |
+
"model.layers.25.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 430 |
+
"model.layers.25.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 431 |
+
"model.layers.25.mlp.up_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 432 |
+
"model.layers.25.mlp.up_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 433 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 434 |
+
"model.layers.25.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 435 |
+
"model.layers.25.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 436 |
+
"model.layers.25.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 437 |
+
"model.layers.25.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 438 |
+
"model.layers.25.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 439 |
+
"model.layers.25.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 440 |
+
"model.layers.25.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 441 |
+
"model.layers.25.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 442 |
+
"model.layers.25.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 443 |
+
"model.layers.25.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 444 |
+
"model.layers.25.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 445 |
+
"model.layers.25.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 446 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 447 |
+
"model.layers.26.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 448 |
+
"model.layers.26.mlp.down_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 449 |
+
"model.layers.26.mlp.down_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 450 |
+
"model.layers.26.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 451 |
+
"model.layers.26.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 452 |
+
"model.layers.26.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 453 |
+
"model.layers.26.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 454 |
+
"model.layers.26.mlp.up_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 455 |
+
"model.layers.26.mlp.up_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 456 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 457 |
+
"model.layers.26.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 458 |
+
"model.layers.26.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 459 |
+
"model.layers.26.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 460 |
+
"model.layers.26.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 461 |
+
"model.layers.26.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 462 |
+
"model.layers.26.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 463 |
+
"model.layers.26.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 464 |
+
"model.layers.26.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 465 |
+
"model.layers.26.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 466 |
+
"model.layers.26.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 467 |
+
"model.layers.26.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 468 |
+
"model.layers.26.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 469 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 470 |
+
"model.layers.27.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 471 |
+
"model.layers.27.mlp.down_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 472 |
+
"model.layers.27.mlp.down_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 473 |
+
"model.layers.27.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 474 |
+
"model.layers.27.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 475 |
+
"model.layers.27.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 476 |
+
"model.layers.27.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 477 |
+
"model.layers.27.mlp.up_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 478 |
+
"model.layers.27.mlp.up_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 479 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 480 |
+
"model.layers.27.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 481 |
+
"model.layers.27.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 482 |
+
"model.layers.27.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 483 |
+
"model.layers.27.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 484 |
+
"model.layers.27.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 485 |
+
"model.layers.27.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 486 |
+
"model.layers.27.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 487 |
+
"model.layers.27.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 488 |
+
"model.layers.27.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 489 |
+
"model.layers.27.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 490 |
+
"model.layers.27.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 491 |
+
"model.layers.27.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 492 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 493 |
+
"model.layers.28.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 494 |
+
"model.layers.28.mlp.down_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 495 |
+
"model.layers.28.mlp.down_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 496 |
+
"model.layers.28.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 497 |
+
"model.layers.28.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 498 |
+
"model.layers.28.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 499 |
+
"model.layers.28.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 500 |
+
"model.layers.28.mlp.up_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 501 |
+
"model.layers.28.mlp.up_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 502 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 503 |
+
"model.layers.28.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 504 |
+
"model.layers.28.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 505 |
+
"model.layers.28.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 506 |
+
"model.layers.28.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 507 |
+
"model.layers.28.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 508 |
+
"model.layers.28.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 509 |
+
"model.layers.28.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 510 |
+
"model.layers.28.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 511 |
+
"model.layers.28.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 512 |
+
"model.layers.28.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 513 |
+
"model.layers.28.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 514 |
+
"model.layers.28.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 515 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 516 |
+
"model.layers.29.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 517 |
+
"model.layers.29.mlp.down_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 518 |
+
"model.layers.29.mlp.down_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 519 |
+
"model.layers.29.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 520 |
+
"model.layers.29.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 521 |
+
"model.layers.29.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 522 |
+
"model.layers.29.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 523 |
+
"model.layers.29.mlp.up_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 524 |
+
"model.layers.29.mlp.up_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 525 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 526 |
+
"model.layers.29.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 527 |
+
"model.layers.29.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 528 |
+
"model.layers.29.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 529 |
+
"model.layers.29.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 530 |
+
"model.layers.29.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 531 |
+
"model.layers.29.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 532 |
+
"model.layers.29.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 533 |
+
"model.layers.29.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 534 |
+
"model.layers.29.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 535 |
+
"model.layers.29.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 536 |
+
"model.layers.29.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 537 |
+
"model.layers.29.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 538 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 539 |
+
"model.layers.3.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 540 |
+
"model.layers.3.mlp.down_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 541 |
+
"model.layers.3.mlp.down_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 542 |
+
"model.layers.3.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 543 |
+
"model.layers.3.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 544 |
+
"model.layers.3.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 545 |
+
"model.layers.3.mlp.up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 546 |
+
"model.layers.3.mlp.up_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 547 |
+
"model.layers.3.mlp.up_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 548 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 549 |
+
"model.layers.3.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 550 |
+
"model.layers.3.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 551 |
+
"model.layers.3.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 552 |
+
"model.layers.3.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 553 |
+
"model.layers.3.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 554 |
+
"model.layers.3.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 555 |
+
"model.layers.3.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 556 |
+
"model.layers.3.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 557 |
+
"model.layers.3.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 558 |
+
"model.layers.3.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 559 |
+
"model.layers.3.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 560 |
+
"model.layers.3.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 561 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 562 |
+
"model.layers.30.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 563 |
+
"model.layers.30.mlp.down_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 564 |
+
"model.layers.30.mlp.down_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 565 |
+
"model.layers.30.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 566 |
+
"model.layers.30.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 567 |
+
"model.layers.30.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 568 |
+
"model.layers.30.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 569 |
+
"model.layers.30.mlp.up_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 570 |
+
"model.layers.30.mlp.up_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 571 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 572 |
+
"model.layers.30.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 573 |
+
"model.layers.30.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 574 |
+
"model.layers.30.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 575 |
+
"model.layers.30.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 576 |
+
"model.layers.30.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 577 |
+
"model.layers.30.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 578 |
+
"model.layers.30.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 579 |
+
"model.layers.30.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 580 |
+
"model.layers.30.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 581 |
+
"model.layers.30.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 582 |
+
"model.layers.30.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 583 |
+
"model.layers.30.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 584 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 585 |
+
"model.layers.31.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 586 |
+
"model.layers.31.mlp.down_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 587 |
+
"model.layers.31.mlp.down_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 588 |
+
"model.layers.31.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 589 |
+
"model.layers.31.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 590 |
+
"model.layers.31.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 591 |
+
"model.layers.31.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 592 |
+
"model.layers.31.mlp.up_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 593 |
+
"model.layers.31.mlp.up_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 594 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 595 |
+
"model.layers.31.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 596 |
+
"model.layers.31.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 597 |
+
"model.layers.31.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 598 |
+
"model.layers.31.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 599 |
+
"model.layers.31.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 600 |
+
"model.layers.31.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 601 |
+
"model.layers.31.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 602 |
+
"model.layers.31.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 603 |
+
"model.layers.31.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 604 |
+
"model.layers.31.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
|
| 605 |
+
"model.layers.31.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
|
| 606 |
+
"model.layers.31.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
|
| 607 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 608 |
+
"model.layers.4.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 609 |
+
"model.layers.4.mlp.down_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 610 |
+
"model.layers.4.mlp.down_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 611 |
+
"model.layers.4.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 612 |
+
"model.layers.4.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 613 |
+
"model.layers.4.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 614 |
+
"model.layers.4.mlp.up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 615 |
+
"model.layers.4.mlp.up_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 616 |
+
"model.layers.4.mlp.up_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 617 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 618 |
+
"model.layers.4.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 619 |
+
"model.layers.4.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 620 |
+
"model.layers.4.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 621 |
+
"model.layers.4.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 622 |
+
"model.layers.4.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 623 |
+
"model.layers.4.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 624 |
+
"model.layers.4.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 625 |
+
"model.layers.4.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 626 |
+
"model.layers.4.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 627 |
+
"model.layers.4.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 628 |
+
"model.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 629 |
+
"model.layers.4.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 630 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 631 |
+
"model.layers.5.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 632 |
+
"model.layers.5.mlp.down_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 633 |
+
"model.layers.5.mlp.down_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 634 |
+
"model.layers.5.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 635 |
+
"model.layers.5.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 636 |
+
"model.layers.5.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 637 |
+
"model.layers.5.mlp.up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 638 |
+
"model.layers.5.mlp.up_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 639 |
+
"model.layers.5.mlp.up_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 640 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 641 |
+
"model.layers.5.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 642 |
+
"model.layers.5.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 643 |
+
"model.layers.5.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 644 |
+
"model.layers.5.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 645 |
+
"model.layers.5.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 646 |
+
"model.layers.5.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 647 |
+
"model.layers.5.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 648 |
+
"model.layers.5.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 649 |
+
"model.layers.5.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 650 |
+
"model.layers.5.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 651 |
+
"model.layers.5.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 652 |
+
"model.layers.5.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 653 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 654 |
+
"model.layers.6.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 655 |
+
"model.layers.6.mlp.down_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 656 |
+
"model.layers.6.mlp.down_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 657 |
+
"model.layers.6.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 658 |
+
"model.layers.6.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 659 |
+
"model.layers.6.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 660 |
+
"model.layers.6.mlp.up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 661 |
+
"model.layers.6.mlp.up_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 662 |
+
"model.layers.6.mlp.up_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 663 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 664 |
+
"model.layers.6.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 665 |
+
"model.layers.6.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 666 |
+
"model.layers.6.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 667 |
+
"model.layers.6.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 668 |
+
"model.layers.6.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 669 |
+
"model.layers.6.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 670 |
+
"model.layers.6.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 671 |
+
"model.layers.6.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 672 |
+
"model.layers.6.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 673 |
+
"model.layers.6.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 674 |
+
"model.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 675 |
+
"model.layers.6.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 676 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 677 |
+
"model.layers.7.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 678 |
+
"model.layers.7.mlp.down_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 679 |
+
"model.layers.7.mlp.down_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 680 |
+
"model.layers.7.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 681 |
+
"model.layers.7.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 682 |
+
"model.layers.7.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 683 |
+
"model.layers.7.mlp.up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 684 |
+
"model.layers.7.mlp.up_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 685 |
+
"model.layers.7.mlp.up_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 686 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 687 |
+
"model.layers.7.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 688 |
+
"model.layers.7.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 689 |
+
"model.layers.7.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 690 |
+
"model.layers.7.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 691 |
+
"model.layers.7.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 692 |
+
"model.layers.7.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 693 |
+
"model.layers.7.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 694 |
+
"model.layers.7.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 695 |
+
"model.layers.7.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 696 |
+
"model.layers.7.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 697 |
+
"model.layers.7.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 698 |
+
"model.layers.7.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 699 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 700 |
+
"model.layers.8.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 701 |
+
"model.layers.8.mlp.down_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 702 |
+
"model.layers.8.mlp.down_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 703 |
+
"model.layers.8.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 704 |
+
"model.layers.8.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 705 |
+
"model.layers.8.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 706 |
+
"model.layers.8.mlp.up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 707 |
+
"model.layers.8.mlp.up_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 708 |
+
"model.layers.8.mlp.up_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 709 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 710 |
+
"model.layers.8.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 711 |
+
"model.layers.8.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 712 |
+
"model.layers.8.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 713 |
+
"model.layers.8.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 714 |
+
"model.layers.8.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 715 |
+
"model.layers.8.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 716 |
+
"model.layers.8.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 717 |
+
"model.layers.8.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 718 |
+
"model.layers.8.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 719 |
+
"model.layers.8.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 720 |
+
"model.layers.8.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 721 |
+
"model.layers.8.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 722 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 723 |
+
"model.layers.9.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 724 |
+
"model.layers.9.mlp.down_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 725 |
+
"model.layers.9.mlp.down_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 726 |
+
"model.layers.9.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 727 |
+
"model.layers.9.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 728 |
+
"model.layers.9.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 729 |
+
"model.layers.9.mlp.up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 730 |
+
"model.layers.9.mlp.up_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 731 |
+
"model.layers.9.mlp.up_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 732 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 733 |
+
"model.layers.9.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 734 |
+
"model.layers.9.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 735 |
+
"model.layers.9.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 736 |
+
"model.layers.9.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 737 |
+
"model.layers.9.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 738 |
+
"model.layers.9.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 739 |
+
"model.layers.9.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 740 |
+
"model.layers.9.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 741 |
+
"model.layers.9.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 742 |
+
"model.layers.9.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
|
| 743 |
+
"model.layers.9.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
|
| 744 |
+
"model.layers.9.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
|
| 745 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
| 746 |
+
}
|
| 747 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "<|im_end|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"32001": {
|
| 39 |
+
"content": "<|im_start|>",
|
| 40 |
+
"lstrip": true,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": true,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
}
|
| 46 |
+
},
|
| 47 |
+
"additional_special_tokens": [],
|
| 48 |
+
"bos_token": "<s>",
|
| 49 |
+
"clean_up_tokenization_spaces": false,
|
| 50 |
+
"eos_token": "</s>",
|
| 51 |
+
"extra_special_tokens": {},
|
| 52 |
+
"legacy": true,
|
| 53 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 54 |
+
"pad_token": "</s>",
|
| 55 |
+
"sp_model_kwargs": {},
|
| 56 |
+
"spaces_between_special_tokens": false,
|
| 57 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 58 |
+
"trust_remote_code": false,
|
| 59 |
+
"unk_token": "<unk>",
|
| 60 |
+
"use_default_system_prompt": true,
|
| 61 |
+
"use_fast": true
|
| 62 |
+
}
|