tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

fix: improve ministral3 docs to be clearer (#3300)

Browse Source 
* fix: improve ministral3 docs to be clearer

* fix: title

* chore: wording
This commit is contained in:
NanoCode012
2025-12-04 21:44:44 +07:00
committed by GitHub
parent 2b66ee189c
commit 5992e607a2
7 changed files with 272 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
examples/ministral/README.md
View File

@@ -1,6 +1,6 @@
# Finetune Ministral with Axolotl
Ministral is a family of openweight models from MistralAI found on HuggingFace at [2410](mistralai/Ministral-8B-Instruct-2410) and [2512](https://huggingface.co/collections/mistralai/ministral-3) (see [Thinking](#thinking)). This guide shows how to fine-tune it with Axolotl with multi-turn conversations and proper masking.
Ministral is a family of openweight models from MistralAI found on [HuggingFace](mistralai/Ministral-8B-Instruct-2410). This guide shows how to fine-tune it with Axolotl with multi-turn conversations and proper masking.
## Getting started
@@ -18,14 +18,6 @@ This config uses about 8.76 GiB VRAM.
Let us know how it goes. Happy finetuning! 🚀
### Thinking
MistralAI has released their [Ministral3 2512](https://huggingface.co/collections/mistralai/ministral-3) model with thinking capabilities, enabling Chain-of-Thought reasoning with explicit thinking steps.
📚 **[See the Thinking fine-tuning guide →](./think/README.md)**
For Ministral3 Base/Instruct, you can reuse the above config to train supervised finetuning.
### Tips
- We recommend adding the same/similar SystemPrompt that the model is tuned for. You can find this within the repo's files titled `SYSTEM_PROMPT.txt`.