Etherll/Qwen2.5-Coder-7B-Instruct-Ties
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
5 derivatives checked
- QuantFactory/Qwen2.5-Coder-7B-3x-Instruct-TIES-v1.0-GGUF: Full fine-tune
- mradermacher/Qwen2.5-Coder-7B-Instruct-Ties-i1-GGUF: Quantization
- mradermacher/Qwen2.5-Coder-7B-Instruct-Ties-GGUF: Same weights, converted
- BenevolenceMessiah/Qwen2.5-Coder-7B-3x-Instruct-TIES-v1.0: Full fine-tune
- BenevolenceMessiah/Qwen2.5-Coder-7B-3x-Instruct-TIES-v1.1: Full fine-tune
1 other repos hold byte-for-byte identical weight files.