BenevolenceMessiah/Yi-Coder-9B-Chat-Instruct-TIES
Full fine-tune vs 01-ai/Yi-Coder-9B. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 72/97, MLP 144/144, Attention 192/192, lm_head 1/1
3 derivatives checked
- mradermacher/Yi-Coder-9B-Chat-Instruct-TIES-i1-GGUF: Quantization
- mradermacher/Yi-Coder-9B-Chat-Instruct-TIES-GGUF: Same weights, converted
- BenevolenceMessiah/Yi-Coder-9B-Chat-Instruct-TIES-MoE-v1.0: MoE built from dense models