Xxiao2023/TCM-Qwen2.5-7B-SFT-V1

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

Tensors changed: Embeddings 0/1, Norms 0/57, MLP 84/84, Attention 112/196, lm_head 1/1

1 derivatives checked

• mradermacher/TCM-Qwen2.5-7B-SFT-V1-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse