powermove72/Shark-Coder-9b

Full fine-tune vs S-miguel/The-Trinity-Coder-7B. Fine-tune: 98% of the weights changed, across 32 of 32 layers.

Tensors changed: MLP 96/96, Attention 128/128, Norms 64/65, Embeddings 1/1, lm_head 0/1

1 derivatives checked

• mradermacher/Shark-Coder-9b-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse