mistralai/Mistral-7B-Instruct-v0.1

Full fine-tune vs mistralai/Mistral-7B-v0.1. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1

19 derivatives checked

• TheBloke/Mistral-7B-Instruct-v0.1-GGUF: Quantization
• mradermacher/Mistral-7B-Instruct-v0.1-i1-GGUF: Quantization
• second-state/Mistral-7B-Instruct-v0.1-GGUF: Quantization
• TheBloke/Mistral-7B-Instruct-v0.1-GPTQ: Quantization
• QuantFactory/Mistral-7B-Instruct-v0.1-GGUF: Quantization
• MaziyarPanahi/Mistral-7B-Instruct-v0.1-GGUF: Quantization
• DevQuasar-8/mistralai.Mistral-7B-Instruct-v0.1-GGUF: Same weights, converted
• mradermacher/Mistral-7B-Instruct-v0.1-GGUF: Quantization
• TheBloke/Mistral-7B-Instruct-v0.1-AWQ: Quantization
• MergekitCloud/mergekit-112: Full fine-tune
• DhruvalLabs/Mistral-7B-Instruct-v0.1-GGUF: Quantization
• GeoGPT-Research-Project/GeoEmbedding: Full fine-tune
• LilithAdam5/Mistral-7B-Instruct-v0.1-GGUF: Quantization
• itlwas/Mistral-7B-Instruct-v0.1-Q4_K_M-GGUF: Quantization
• Commencis/Commencis-LLM: Full fine-tune
• Akshaykumarbm/OpenAssisted-English-Mistral-7b: Full fine-tune
• mehuldamani/RLVR-hotpot-mistral: Full fine-tune
• rhaymison/cuscuz-7b: LoRA-style
• sweatSmile/Mistral-7B-Instruct-v0.1-Sarcasm: Abliterated

13 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse