dipta007/GanitLLM-0.6B_SFT_CGRPO

Full fine-tune vs Qwen/Qwen3-0.6B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 84/113, MLP 84/84, Attention 112/112

1 derivatives checked

• mradermacher/GanitLLM-0.6B_SFT_CGRPO-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse