NarendraK1/CodeLlama-7B-CodeForces-CoTs-SFT

Full fine-tune vs codellama/CodeLlama-7b-Instruct-hf. Fine-tune: 98% of the weights changed, across 32 of 32 layers.

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

1 derivatives checked

• mradermacher/CodeLlama-7B-CodeForces-CoTs-SFT-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse