deepseek-ai/DeepSeek-Coder-V2-Instruct
Full fine-tune vs deepseek-ai/DeepSeek-Coder-V2-Base. Fine-tune: 100% of the weights changed, across 60 of 60 layers.
Tensors changed: Embeddings 1/1, Norms 145/241, lm_head 1/1, Attention 300/300, MLP 2448/2457
8 derivatives checked
- bartowski/DeepSeek-Coder-V2-Instruct-GGUF: Quantization
- gaianet/DeepSeek-Coder-V2-Instruct-GGUF: Same weights, converted
- legraphista/DeepSeek-Coder-V2-Instruct-IMat-GGUF: Quantization
- second-state/DeepSeek-Coder-V2-Instruct-GGUF: Same weights, converted
- qwp4w3hyb/DeepSeek-Coder-V2-Instruct-iMat-GGUF: Quantization
- nisten/deepseek-coder-v2-inst-cpu-optimized-gguf: Same weights, converted
- GGorman/DeepSeek-Coder-V2-Instruct-Q4-mlx: Quantization
- Ocean82/deepseek-coder-v2-inst-cpu-optimized-gguf: Same weights, converted