lainlives/deepseek_ai_deepseek_coder_v2_lite_instruct-nl2sqlpp-16bit-v4.0-cw-4K-GGUF

Same weights, converted vs jastorj/deepseek_ai_deepseek_coder_v2_lite_instruct-nl2sqlpp-16bit-v4.0-cw-4K. Same weights stored in another dtype (BF16 → BF16/F32), plus 132 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/82, lm_head 0/1, Attention 0/81, MLP 0/107

On the Hub · Downloads on Model Pulse