vicharai/ViCoder-html-32B-preview
LoRA-style vs Qwen/Qwen2.5-Coder-32B-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 64 of 64 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/129, MLP 192/192, Attention 256/448, lm_head 0/1
4 derivatives checked
- mradermacher/ViCoder-html-32B-preview-i1-GGUF: Quantization
- mradermacher/ViCoder-html-32B-preview-GGUF: Quantization
- mradermacher/DhruvHtml-32B-GGUF: Quantization
- vicharai/ViCoder-html-32B-preview-GGUF: Quantization