ri-char/rldecompile-1.3b

Full fine-tune vs LLM4Binary/llm4decompile-1.3b-v1.5. Fine-tune: 95% of the weights changed, across 24 of 24 layers.

Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 0/49, MLP 72/72, Attention 96/96

1 derivatives checked

• mradermacher/rldecompile-1.3b-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse