snapcart-ai/sam-1-base
LoRA-style vs Qwen/Qwen2.5-7B-Instruct. 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 16 of 28 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 48/84, Attention 64/196, lm_head 0/1
2 derivatives checked
- mradermacher/sam-1-base-i1-GGUF: Quantization
- mradermacher/sam-1-base-GGUF: Same weights, converted