Instruct-LoRA-r16-AllLinear
This is a LoRA extracted from a language model. It was extracted using mergekit.
LoRA Details
This LoRA adapter was extracted from mistralai/Ministral-3-8B-Instruct-2512-BF16 and uses mistralai/Ministral-3-8B-Base-2512 as a base.
Parameters
The following command was used to extract this LoRA adapter:
/usr/local/bin/mergekit-extract-lora --model mistralai/Ministral-3-8B-Instruct-2512-BF16 --base-model mistralai/Ministral-3-8B-Base-2512 --out-path /content/Instruct-LoRA-r16-AllLinear --max-rank 16 --device cuda --exclude-regex (lm_head|embed_tokens|norm|ln_pre|ln_post|patch_conv)
- Downloads last month
- 23
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for aitf-its-tim3-dfk/instruct-ministral-3-8b-extract
Base model
mistralai/Ministral-3-8B-Base-2512