apple/DiffuCoder-7B-Base
Full fine-tune vs Qwen/Qwen2.5-Coder-7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196, lm_head 1/1
4 derivatives checked
- mradermacher/DiffuCoder-7B-Base-i1-GGUF: Quantization
- Mungert/DiffuCoder-7B-Instruct-GGUF: Full fine-tune
- apple/DiffuCoder-7B-Instruct: Full fine-tune
- mradermacher/DiffuCoder-7B-Base-GGUF: Same weights, converted