README.md

---
License: apache-2.0
Language:
- En
Pipeline_tag: text-generation
Base_model: nvidia/Llama-3.1-Minitron-4 B-Width-Base
Tags:
- Chat
license: agpl-3.0
datasets:
- anthracite-org/kalo-opus-instruct-22k-no-refusal
- PJMixers/lodrick-the-lafted_OpusStories-ShareGPT
- NewEden/Gryphe-3.5-16k-Subset
- Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
tags:
- chat
---



A model made to continue off my previous work on [Magnum 4B](https://huggingface.co/anthracite-org/magnum-v2-4b), A small model made for creative writing / General assistant tasks, finetuned ontop of [IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml](https://huggingface.co/IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml), this model is made to be more coherent and generally be better then the 4B at both writing and assistant tasks. 

# Quants 

GGUF: https://huggingface.co/NewEden/Holland-4B-gguf

EXL2: https://huggingface.co/NewEden/Holland-4B-exl2


## Prompting
Model has been Instruct tuned with the ChatML formatting. A typical input would look like this:

```py
"""<|im_start|>system
system prompt<|im_end|>
<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
<|im_start|>assistant
"""
```

## Support

## No longer needed as LCPP has merged support - just update.

To run inference on this model, you'll need to use Aphrodite, vLLM or EXL 2/tabbyAPI, as llama.cpp hasn't yet merged the required pull request to fix the llama 3.1 rope_freqs issue with custom head dimensions. 

However, you can work around this by quantizing the model yourself to create a functional GGUF file. Note that until [this PR](https://github.com/ggerganov/llama.cpp/pull/9141) is merged, the context will be limited to 8 k tokens.

To create a working GGUF file, make the following adjustments:

1. Remove the `"rope_scaling": {}` entry from `config.json`
2. Change `"max_position_embeddings"` to `8192` in `config.json`

These modifications should allow you to use the model with llama. Cpp, albeit with the mentioned context limitation.

## Axolotl config

<details><summary>See axolotl config</summary>

Axolotl version: `0.4.1`
```yaml
base_model: IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/Gryphe-3.5-16k-Subset
    type: sharegpt
    conversation: chatml
  - path: Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
    type: sharegpt
    conversation: chatml
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: sharegpt
    conversation: chatml
  - path: PJMixers/lodrick-the-lafted_OpusStories-ShareGPT
    type: sharegpt
    conversation: chatml

chat_template: chatml

val_set_size: 0.01
output_dir: ./outputs/out

adapter:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:

sequence_len: 16384
# sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true

wandb_project: 
wandb_entity:
wandb_watch:
wandb_name: 
wandb_log_model:

gradient_accumulation_steps: 32
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit
#optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.00002
weight_decay: 0.05

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_ratio: 0.1
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1

debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero2.json
#deepspeed:
fsdp:
fsdp_config:

special_tokens:
  pad_token: <|finetune_right_pad_id|>

```

</details><br>

## Credits

- [anthracite-org/kalo-opus-instruct-22k-no-refusal](https://huggingface.co/datasets/anthracite-org/kalo-opus-instruct-22k-no-refusal)
- [NewEden/Gryphe-3.5-16k-Subset](https://huggingface.co/datasets/NewEden/Gryphe-3.5-16k-Subset) 
- [Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned](https://huggingface.co/datasets/Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned)
- [lodrick-the-lafted/OpusStories](https://huggingface.co/datasets/lodrick-the-lafted/OpusStories)


## Training
The training was done for 2 epochs. We used  2 x [RTX 6000s](https://store.nvidia.com/en-us/nvidia-rtx/products/nvidia-rtx-6000-ada-generation/) GPUs graciously provided by [Kubernetes_Bad](https://huggingface.co/kubernetes-bad) for the full-parameter fine-tuning of the model. 

[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)