ApolloRaines/Qwen2.5-Coder-32B-Instruct-Jbliterated

Full fine-tune vs Qwen/Qwen2.5-Coder-32B-Instruct. Fine-tune: 98% of the weights changed, across 64 of 64 layers.

Tensors changed: Embeddings 0/1, Norms 0/129, MLP 192/192, Attention 256/448, lm_head 1/1

On the Hub · Downloads on Model Pulse