Rombo-Org/Rombo-LLM-V3.0-Qwen-72b

Full fine-tune vs Rombo-Org/Rombo-LLM-V2.5-Qwen-72b. Fine-tune: 100% of the weights changed, across 80 of 80 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 112/161, MLP 240/240, Attention 559/560

3 derivatives checked

• bartowski/Rombo-Org_Rombo-LLM-V3.0-Qwen-72b-GGUF: Quantization
• mradermacher/Rombo-LLM-V3.0-Qwen-72b-i1-GGUF: Quantization
• mradermacher/Rombo-LLM-V3.0-Qwen-72b-GGUF: Quantization

On the Hub · Downloads on Model Pulse