apple/sage-ft-mixtral-8x7b
LoRA-style vs mistralai/Mixtral-8x7B-Instruct-v0.1. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of q_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, MLP 0/768, other 0/32, Norms 0/65, Attention 64/128, lm_head 0/1
1 derivatives checked
- DevQuasar/apple.sage-ft-mixtral-8x7b-GGUF: Same weights, converted