JosephNguyen/Sailor2-8B-Chat-finetuned
LoRA-style vs sail/Sailor2-8B-Chat. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 96/96, Attention 128/224, lm_head 0/1
1 derivatives checked
- mradermacher/Sailor2-8B-Chat-finetuned-GGUF: Same weights, converted