legraphista/DeepSeek-Coder-V2-Lite-Base-IMat-GGUF

Same weights, converted vs deepseek-ai/DeepSeek-Coder-V2-Lite-Base. Same weights stored in another dtype (BF16 → F16/F32), plus 78 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/82, lm_head 0/1, Attention 0/108, MLP 0/107

On the Hub · Downloads on Model Pulse