xxwu/Agent-STAR-RL-7B

Full fine-tune vs Qwen/Qwen2.5-7B-Instruct. Fine-tune: 93% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 53/57, MLP 84/84, Attention 196/196, lm_head 1/1

2 derivatives checked

• mradermacher/Agent-STAR-RL-7B-i1-GGUF: Quantization
• mradermacher/Agent-STAR-RL-7B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse