hpcgroup/hpc-coder-v2-16b

Full fine-tune vs deepseek-ai/DeepSeek-Coder-V2-Lite-Base. Fine-tune: 100% of the weights changed, across 27 of 27 layers.

Tensors changed: Embeddings 1/1, Norms 26/82, lm_head 1/1, Attention 108/108, MLP 2808/2808

4 derivatives checked

• mradermacher/hpc-coder-v2-16b-i1-GGUF: Quantization
• nicoboss/hpc-coder-v2-16b-non-MLA-i1-GGUF: Quantization
• mradermacher/hpc-coder-v2-16b-GGUF: Quantization
• nicoboss/hpc-coder-v2-16b-non-MLA-GGUF: Quantization

On the Hub · Downloads on Model Pulse