luzimu/WebGen-LM-32B

Different architecture vs Qwen/Qwen2.5-Coder-7B-Instruct. Different architecture: only 0 of 339/771 tensors match by name and shape.

2 derivatives checked

• mradermacher/WebGen-LM-32B-i1-GGUF: Quantization
• mradermacher/WebGen-LM-32B-GGUF: Quantization

On the Hub · Downloads on Model Pulse