deepseek-ai/DeepSeek-Coder-V2-Instruct-0724
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 241/241, lm_head 1/1, Attention 300/300, MLP 2457/2457
4 derivatives checked
- bartowski/DeepSeek-Coder-V2-Instruct-0724-GGUF: Quantization
- lmstudio-community/DeepSeek-Coder-V2-Instruct-0724-GGUF: Quantization
- legraphista/DeepSeek-Coder-V2-Instruct-0724-IMat-GGUF: Quantization
- mradermacher/DeepSeek-Coder-V2-Instruct-0724-i1-GGUF: Quantization