---
license: apache-2.0
language:
  - en
pipeline_tag: text-generation
tags:
  - chat
---

## This repo contains EXL2 quants of the model. If you need the original weights, please find them [here](https://huggingface.co/anthracite-org/magnum-v2-4b).
## Base repo only contains the measurement file, see revisions for your quant of choice.

- [measurement.json](https://huggingface.co/anthracite-org/magnum-v2-4b-exl2/tree/main)
- [3.0bpw](https://huggingface.co/anthracite-org/magnum-v2-4b-exl2/tree/3.0bpw)
- [4.0bpw](https://huggingface.co/anthracite-org/magnum-v2-4b-exl2/tree/4.0bpw)
- [5.0bpw](https://huggingface.co/anthracite-org/magnum-v2-4b-exl2/tree/5.0bpw)
- [6.0bpw](https://huggingface.co/anthracite-org/magnum-v2-4b-exl2/tree/6.0bpw)
- [8.0bpw](https://huggingface.co/anthracite-org/magnum-v2-4b-exl2/tree/8.0bpw)

![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 or 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.

## 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](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
...