HuggingFaceH4/mistral-7b-sft-beta
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 17/65, MLP 96/96, Attention 128/128, lm_head 1/1
6 derivatives checked
- MaziyarPanahi/mistral-7b-sft-beta-GGUF: Quantization
- mradermacher/mistral-7b-sft-beta-i1-GGUF: Quantization
- mradermacher/mistral-7b-sft-beta-GGUF: Same weights, converted
- Mihaiii/Metis-0.1: LoRA-style
- AIR-hl/Mistral-7B-Base-WPO-bf16: Full fine-tune
- Katayoon/DPO-ONLY-Zephyr-7B: Full fine-tune