README.md

---

license: apache-2.0
language:
  - en
pipeline_tag: text-generation
base_model: nvidia/Llama-3.1-Minitron-4B-Width-Base
tags:
  - chat

---

![](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)

# QuantFactory/magnum-v2-4b-GGUF
This is quantized version of [anthracite-org/magnum-v2-4b](https://huggingface.co/anthracite-org/magnum-v2-4b) created using llama.cpp

# Original Model Card


![image/png](https://cdn-uploads.huggingface.co/production/uploads/658a46cbfb9c2bdfae75b3a6/9JwXZze4tHRGpc_RzE2AU.png)
This is the eighth in a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus. This model is fine-tuned on top of [IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml](https://huggingface.co/IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml).

## 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

To run inference on this model, you'll need to use Aphrodite, vLLM or EXL2/tabbyAPI, as llama.cpp hasn't yet merged the required pull request to fix the llama3.1 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 8k 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: anthracite-org/Gryphe-3.5-16k-Subset
    type: sharegpt
    conversation: chatml
  - path: Epiculous/Synthstruct-Gens-v1-Filtered-n-Cleaned
    type: sharegpt
    conversation: chatml
  - path: anthracite-org/Stheno-Data-Filtered
    type: sharegpt
    conversation: chatml
  - path: Epiculous/SynthRP-Gens-v1-Filtered-n-Cleaned
    type: sharegpt
    conversation: chatml
  - path: lodrick-the-lafted/NopmWritingStruct
    type: sharegpt
    conversation: chatml
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    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

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
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:
fsdp:
fsdp_config:

special_tokens:
  pad_token: <|finetune_right_pad_id|>

```

</details><br>

## Credits

- [anthracite-org/Stheno-Data-Filtered](https://huggingface.co/datasets/anthracite-org/Stheno-Data-Filtered)
- [anthracite-org/kalo-opus-instruct-22k-no-refusal](https://huggingface.co/datasets/anthracite-org/kalo-opus-instruct-22k-no-refusal)
- [lodrick-the-lafted/NopmWritingStruct](https://huggingface.co/datasets/lodrick-the-lafted/NopmWritingStruct)
- [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)
- [Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned](https://huggingface.co/datasets/Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned)

This model has been a team effort, and the credits goes to all members of Anthracite.

## 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)

## Safety
...