01-ai/Yi-Coder-9B-Chat
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 79/97, MLP 144/144, Attention 192/192, lm_head 1/1
12 derivatives checked
- MaziyarPanahi/Yi-Coder-9B-Chat-GGUF: Same weights, converted
- bartowski/Yi-Coder-9B-Chat-GGUF: Same weights, converted
- mradermacher/Yi-Coder-9B-Chat-i1-GGUF: Quantization
- mradermacher/Yi-Coder-9B-Chat-GGUF: Same weights, converted
- legraphista/Yi-Coder-9B-Chat-IMat-GGUF: Same weights, converted
- lmstudio-community/Yi-Coder-9B-Chat-GGUF: Quantization
- second-state/Yi-Coder-9B-Chat-GGUF: Same weights, converted
- CISCai/Yi-Coder-9B-Chat-SOTA-GGUF: Same weights, converted
- gaianet/Yi-Coder-9B-Chat-GGUF: Same weights, converted
- tensorblock/Yi-Coder-9B-Chat-GGUF: Quantization
- stelterlab/Yi-Coder-9B-Chat-AWQ: Quantization
- BenevolenceMessiah/Yi-Coder-9B-Chat-8x-MoE: MoE built from dense models
1 other repos hold byte-for-byte identical weight files.