grimjim/Mistral-7B-Instruct-demi-merge-v0.2-7B
Full fine-tune vs mistral-community/Mistral-7B-v0.2. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 16/65, MLP 96/96, Attention 128/128, lm_head 1/1
5 derivatives checked
- bartowski/kunoichi-lemon-royale-v2-32K-7B-GGUF: Full fine-tune
- mradermacher/Mistral-7B-Instruct-demi-merge-v0.2-7B-i1-GGUF: Quantization
- mradermacher/Mistral-7B-Instruct-demi-merge-v0.2-7B-GGUF: Same weights, converted
- grimjim/kunoichi-lemon-royale-v2-32K-7B: Full fine-tune
- grimjim/kukulemon-32K-7B: Full fine-tune