WhiteRabbitNeo/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B
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 54/57, MLP 84/84, Attention 196/196, lm_head 1/1
6 derivatives checked
- bartowski/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B-GGUF: Same weights, converted
- mradermacher/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B-GGUF: Same weights, converted
- yur968869/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B-GGUF: Same weights, converted
- MaziyarPanahi/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B-GGUF: Same weights, converted
- tensorblock/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B-GGUF: Quantization
- win10/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-12.3B: Partial fine-tune (fewer layers)