mistralai/Mistral-7B-Instruct-v0.3
Full fine-tune vs mistralai/Mistral-7B-v0.3. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 18/65, MLP 96/96, Attention 128/128, lm_head 1/1
106 derivatives checked
- MaziyarPanahi/Mistral-7B-Instruct-v0.3-GGUF: Same weights, converted
- solidrust/Mistral-7B-Instruct-v0.3-AWQ: Quantization
- unsloth/mistral-7b-instruct-v0.3-bnb-4bit: Quantization
- lmstudio-community/Mistral-7B-Instruct-v0.3-GGUF: Quantization
- QuantFactory/Mistral-7B-Instruct-v0.3-GGUF: Quantization
- sallani/ELISARCyberAIEdge7B-LoRA-GGUF: Not comparable yet
- saidutta69/Mistral-7B-Instruct-v0.3-heretic: Abliterated
- SanctumAI/Mistral-7B-Instruct-v0.3-GGUF: Same weights, converted
- mradermacher/Mistral-7B-Instruct-v0.3-i1-GGUF: Quantization
- RedHatAI/Mistral-7B-Instruct-v0.3-GPTQ-4bit: Quantization
- second-state/Mistral-7B-Instruct-v0.3-GGUF: Same weights, converted
- simpledirect/Vinci-Prova-7B-1.0: LoRA-style
- mradermacher/Mistral-7B-Instruct-v0.3-GGUF: Same weights, converted
- legraphista/Mistral-7B-Instruct-v0.3-IMat-GGUF: Same weights, converted
- jfer1015/Mistral-7B-Instruct-v0.3-Q4_K_M-GGUF: Quantization
- QuantFactory/Mistral-7B-Instruct-Uz-GGUF: Full fine-tune
- Sanorian/Mistral-7B-4bit-1C-MLX: Quantization
- castorini/first_mistral: Full fine-tune
- millat/mistral-7b-indian-university-guidance: Quantization
- DeviantArtist031/grok-oss-7B: LoRA-style
- c4tdr0ut/grok-oss-7B: LoRA-style
- noctrex/Mistral-7B-Instruct-v0.3-abliterated-GGUF: Abliterated
- ApolloRaines/Mistral-7B-Instruct-v0.3-Parasite: Full fine-tune
- TushaeBXN/Nia-Mistral-7B-V1: Not comparable yet
- Raymond-dev-546730/Research-Reasoner-7B-v0.3: Full fine-tune
- CISCai/Mistral-7B-Instruct-v0.3-SOTA-GGUF: Same weights, converted
- DuoNeural/Mistral-7B-Instruct-v0.3-GGUF: Same weights, converted
- ApolloRaines/Mistral-7B-Parasite: Full fine-tune
- ApolloRaines/Mistral-7B-Instruct-v0.3-Jbliterated: Full fine-tune
- plawanrath/mistral-7b-instruct-v0.3-q8-mlx-cba: Quantization