cerebras/Qwen3-Coder-REAP-363B-A35B
LoRA-style vs Qwen/Qwen3-Coder-480B-A35B-Instruct. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, up_proj changed, in 62 of 62 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, MLP 1796/1830, Norms 0/249, Attention 0/248, lm_head 0/1
1 derivatives checked
- unsloth/Qwen3-Coder-REAP-363B-A35B-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.