rhaymison/Mistral-portuguese-luana-7b-mental-health
LoRA-style vs rhaymison/Mistral-portuguese-luana-7b. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of gate_proj, k_proj, o_proj, q_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 32/96, Attention 128/128, lm_head 0/1
1 derivatives checked
- mradermacher/Mistral-portuguese-luana-7b-mental-health-GGUF: Same weights, converted