eth-nlped/TutorRL-7B-think

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 48/57, MLP 84/84, Attention 196/196, lm_head 1/1

2 derivatives checked

• mradermacher/TutorRL-7B-think-i1-GGUF: Quantization
• mradermacher/TutorRL-7B-think-GGUF: Same weights, converted

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse