Xiaojian9992024/Qwen2.5-THREADRIPPER-Medium-Censored

Full fine-tune vs rombodawg/Rombos-LLM-V2.6-Qwen-14b. Fine-tune: 100% of the weights changed, across 48 of 48 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 69/97, MLP 144/144, Attention 334/336

1 derivatives checked

• mradermacher/Qwen2.5-THREADRIPPER-Medium-Censored-GGUF: Quantization

On the Hub · Downloads on Model Pulse