A conservatively abliterated Mistral-7B-Instruct-v0.3 with reduced refusals, an extended 32K vocabulary, function calling, and preserved instruction-following quality.
Quantized Mistral 7B Instruct models optimized for fast, CPU-only local inference with Ollama. Multiple variants balancing speed, quality, and memory efficiency.
https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3
Fixed num_ctx to 32768. This Mistral 7B v0.2 Instruct model is ready to use for full model's 32k contexts window.
A finetuned version of Mistral-7B-Instruct-v0.2 on a instruct portuguese dataset, as an attempt to improve the performance of the model on the language. HF Page: cnmoro/Mistral-7B-Portuguese
pulled from https://huggingface.co/MaziyarPanahi/mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.2-slerp-GGUF
quantization of perlthoughts/Mistral-7B-Instruct-v0.2-2x7B-MoE
https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF : mistral-7b-instruct-v0.1.Q3_K_M.gguf
This is mistralai/Mistral-7B-Instruct-v0.2 with layers interleaved to make a bigger 12b model
Quantized version of malhajar/Mistral-7B-Instruct-v0.2-turkish HF model
finetuned : python -m mlx_lm.lora --train --model mistralai/Mistral-7B-Instruct-v0.3 --batch-size 4 --fine-tune-type dora --iters 1000 --num-layers 16
Mistral-7B-v0.3-Chinese is an instruction-tuned language model for Chinese & English users with various abilities such as roleplaying & tool-using built upon the Mistral-7B-Instruct-v0.3.
This is a Bulgarian language model developed by INSAIT, built on top of Mistral 7B and fine-tuned specifically for instruction-following tasks in Bulgarian. It’s optimized for high-quality responses and conversational use.
🥐 Mistral-7B-v0.3-Chinese-Chat is an instruction-tuned language model for Chinese & English users with various abilities such as roleplaying & tool-using built upon the mistralai/Mistral-7B-Instruct-v0.3.
Mistral 7b-instruct tuned with Q&A from NIST AI RMF 1.0, MITRE ATLAS, OWASP AI Periodic Table and Google SAIM framework.