|
--- |
|
base_model: mistralai/Mistral-Small-24B-Instruct-2501 |
|
datasets: |
|
- ServiceNow-AI/R1-Distill-SFT |
|
tags: |
|
- text-generation-inference |
|
- transformers |
|
- unsloth |
|
- mistral |
|
- trl |
|
- sft |
|
license: apache-2.0 |
|
language: |
|
- en |
|
--- |
|
|
|
<picture> |
|
<img alt="image" src="https://huggingface.co/tensopolis/assets/resolve/main/logo_512.png"> |
|
</picture> |
|
|
|
## mistral-small-r1-tensopolis |
|
|
|
This model is a **reasoning** fine-tune of unsloth/**mistral-small-24b-instruct-2501**-unsloth-bnb-4bit. Trained in **1xA100** for about **100 hours**. Please refer to the base model and dataset for more information about license, prompt format, etc. |
|
|
|
Base model: [**mistralai/Mistral-Small-24B-Instruct-2501**](https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501) |
|
|
|
Dataset: [**ServiceNow-AI/R1-Distill-SFT**](https://huggingface.co/datasets/ServiceNow-AI/R1-Distill-SFT) |
|
|
|
#### Basic Instruct Template (V7-Tekken) |
|
|
|
``` |
|
<s>[SYSTEM_PROMPT]<system prompt>[/SYSTEM_PROMPT][INST]<user message>[/INST]<assistant response></s>[INST]<user message>[/INST] |
|
``` |
|
|
|
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. |
|
|
|
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) |
|
|
