Create README.md

README.md

@@ -0,0 +1,56 @@
+---
+license: other
+license_name: tongyi-qianwen
+license_link: https://huggingface.co/Qwen/Qwen2-72B-Instruct/blob/main/LICENSE
+language:
+- en
+- zh
+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-32b-v1).
+## Base repo only contains the measurement file, see revisions for your quant of choice.
+
+- [measurement.json](https://huggingface.co/anthracite-org/magnum-32b-v2-exl2/tree/main)
+- [3.0bpw](https://huggingface.co/anthracite-org/magnum-32b-v2-exl2/tree/3.0bpw)
+- [4.0bpw](https://huggingface.co/anthracite-org/magnum-32b-v2-exl2/tree/4.0bpw)
+- [5.0bpw](https://huggingface.co/anthracite-org/magnum-32b-v2-exl2/tree/5.0bpw) (uploading soon)
+- [6.0bpw](https://huggingface.co/anthracite-org/magnum-32b-v2-exl2/tree/6.0bpw) (uploading soon)
+- [8.0bpw](https://huggingface.co/anthracite-org/magnum-32b-v2-exl2/tree/8.0bpw) (uploading soon)
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/658a46cbfb9c2bdfae75b3a6/A9n8EJBDQziJWnXhOYeEE.png)
+
+This is the third 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 [Qwen1.5 32B](https://huggingface.co/Qwen/Qwen1.5-32B).
+
+## Prompting
+Model has been Instruct tuned with the ChatML formatting. A typical input would look like this:
+
+```py
+"""<|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
+"""
+```
+
+## Credits
+
+- [NobodyExistsOnTheInternet/Magpie-Reasoning-Medium-Subset](https://huggingface.co/datasets/NobodyExistsOnTheInternet/Magpie-Reasoning-Medium-Subset)
+- [kalomaze/Opus_Instruct_25k](https://huggingface.co/datasets/kalomaze/Opus_Instruct_25k)
+- [Nopm/Opus_WritingStruct](https://huggingface.co/datasets/Nopm/Opus_WritingStruct)
+- [Gryphe/Sonnet3.5-SlimOrcaDedupCleaned](https://huggingface.co/datasets/Gryphe/Sonnet3.5-SlimOrcaDedupCleaned) (A ~16k rows subset)
+
+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 8x [NVIDIA H100 Tensor Core](https://www.nvidia.com/en-us/data-center/h100/) GPUs 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
+...