mistralai/Mistral-7B-Instruct-v0.2
117 derivatives checked
- TheBloke/Mistral-7B-Instruct-v0.2-GGUF: Quantization
- mozilla-ai/Mistral-7B-Instruct-v0.2-llamafile: Same weights, converted
- abacusai/bigstral-12b-32k: Partial fine-tune (fewer layers)
- TheBloke/Mistral-7B-Instruct-v0.2-AWQ: Quantization
- mradermacher/Mistral-7B-Instruct-v0.2-i1-GGUF: Quantization
- second-state/Mistral-7B-Instruct-v0.2-GGUF: Quantization
- NeuralNovel/Mini-Mixtral-v0.2: MoE built from dense models
- TheBloke/Mistral-7B-Instruct-v0.2-GPTQ: Quantization
- mradermacher/Mistral-7B-Instruct-v0.2-GGUF: Quantization
- dagbs/bigstral-12b-32k-GGUF: Full fine-tune (fewer layers)
- LoneStriker/Mistral-7B-Instruct-v0.2-Neural-Story-GGUF: Full fine-tune
- MaziyarPanahi/Mistral-7B-Instruct-v0.2-GGUF: Quantization
- segolilylabs/Lily-Cybersecurity-7B-v0.2: LoRA-style
- QuantFactory/Mental-Health-FineTuned-Mistral-7B-Instruct-v0.2-GGUF: Full fine-tune
- Zynerji/Ektome-Mistral-7B-Instruct-v0.2-PristinelyUncensored: Abliterated
- QuantFactory/Lily-Cybersecurity-7B-v0.2-GGUF: Full fine-tune
- nold/Mistral-7B-Instruct-v0.2-Neural-Story-GGUF: Full fine-tune
- ogulcanaydogan/Turkish-LLM-7B-Instruct: Full fine-tune
- Kquant03/Mistral-7B-Instruct-v0.2-Neural-Story-GGUF: Full fine-tune
- QuantFactory/bigstral-12b-32k-GGUF: Full fine-tune (fewer layers)
- Jeesup/svd-safety-mis7_swift_jbbcal2_remove40: LoRA-style
- scribis/Fantastica-7b-Instruct-0.2-Italian-GGUF: Full fine-tune
- QuantFactory/Mistral-Gutenberg-Doppel-7B-FFT-GGUF: Full fine-tune
- Jeesup/svd-safety-mis7_swift_remove30: LoRA-style
- Jeesup/svd-safety-mis7_swift_jbbsft10_remove20: LoRA-style
- SGK86/dsi-mistral-7b-searchtome-subset: Full fine-tune
- Jeesup/svd-safety-mis7_swift_jbbcal2_remove30: LoRA-style
- Jeesup/svd-safety-mis7_swift_remove40: LoRA-style
- QuantFactory/Mistral-7B-Instruct-v0.2-GGUF: Quantization
- JonaszPotoniec/mistral-pl-owca: LoRA-style
57 other repos hold byte-for-byte identical weight files.