Downloads · 30 days
6
15% of all-time downloads
Mistral-3.2-Instruct-Antirep-sft-24B-0.1
Nitral-Archive/Mistral-3.2-Instruct-Antirep-sft-24B-0.1
Mistral-3.2-Instruct-Antirep-sft-24B-0.1 is a machine learning model from Nitral-Archive. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
All-time downloads
39
Public
Parameters
24B
48 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors48 GB · 100%
At a glance
- License
- other
- Model type
- mistral3
- Access
- Public
- Created
- Aug 27, 2025
- Updated
- Aug 28, 2025
- SHA
- 46acfd94
Base models
Model card
From the Hugging Face model README
Trained on https://huggingface.co/datasets/Nitral-AI/antirep_sharegpt for 2 epochs at 3e-5, 4bit qlora. at rank/alpha 32.
Original set was created by: "Preference dataset meant to decrease repetition, measured as either copying n-grams from input or infinite / semi-infite repetition of tokens; the chosen split is V3 03/24 instructed to avoid n-gram repetition, while the rejected split consists of either V3 03/24 instructed to copy from the input or Qwen 3 8B with a rep pen of 0.7."
just took the preference rows, removed the rejected, converted to sharegpt jsonl to create the sft version of the set used above.
- Type
- mistral3
- License
- other
- Languages
- en
- Created
- Aug 27, 2025
- Updated
- Aug 28, 2025