LRM-Conta-Detection-Arena/sft-conta-deepseek-distill-qwen2.5-7b

Full fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Qwen-7B. Fine-tune: 93% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 0/1, Attention 196/196, MLP 84/84, Norms 51/57, lm_head 1/1

1 derivatives checked

• mradermacher/sft-conta-deepseek-distill-qwen-7b-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse