rohitanurag/ClinicalGPT-Pubmed-Instruct-V1.0
Partial fine-tune vs mistralai/Mistral-7B-Instruct-v0.2. Partial change: 15% of the weights changed (attention, embeddings, lm_head), in 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 0/65, MLP 0/96, Attention 96/128, lm_head 1/1
2 derivatives checked
- mradermacher/ClinicalGPT-Pubmed-Instruct-V1.0-i1-GGUF: Quantization
- mradermacher/ClinicalGPT-Pubmed-Instruct-V1.0-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.