mradermacher/deepseek-coder-6.7B-kexer-GGUF

Same weights, converted vs JetBrains/deepseek-coder-6.7B-kexer. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128, lm_head 0/1

On the Hub · Downloads on Model Pulse