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

Full fine-tune vs deepseek-ai/deepseek-coder-6.7b-base. bartowski/deepseek-coder-6.7B-kexer-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 12/65, MLP 96/96, Attention 128/128, lm_head 1/1

On the Hub · Downloads on Model Pulse