01-ai/Yi-Coder-1.5B-Chat
Full fine-tune vs 01-ai/Yi-Coder-1.5B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 45/49, MLP 72/72, Attention 96/96
9 derivatives checked
- MaziyarPanahi/Yi-Coder-1.5B-Chat-GGUF: Same weights, converted
- bartowski/Yi-Coder-1.5B-Chat-GGUF: Same weights, converted
- mradermacher/Yi-Coder-1.5B-Chat-i1-GGUF: Quantization
- mradermacher/Yi-Coder-1.5B-Chat-GGUF: Quantization
- second-state/Yi-Coder-1.5B-Chat-GGUF: Same weights, converted
- legraphista/Yi-Coder-1.5B-Chat-IMat-GGUF: Same weights, converted
- lmstudio-community/Yi-Coder-1.5B-Chat-GGUF: Quantization
- gaianet/Yi-Coder-1.5B-Chat-GGUF: Same weights, converted
- unclemusclez/Unsloth-Yi-Coder-1.5B-Chat-Devinator-v1: LoRA-style
1 other repos hold byte-for-byte identical weight files.