aaravriyer193/chimpgpt-coder-elite
LoRA-style vs zai-org/GLM-4.7-Flash. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, kv_a_proj_with_mqa, kv_b_proj, o_proj, q_a_proj, q_b_proj, up_proj changed, in 47 of 47 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/189, MLP 141/2504, Attention 235/235, lm_head 0/1
2 derivatives checked
- mradermacher/chimpgpt-coder-elite-i1-GGUF: Quantization
- mradermacher/chimpgpt-coder-elite-GGUF: Quantization