Rombo-Org/Rombo-LLM-V2.7-llama-3.2-1b
Full fine-tune vs meta-llama/Llama-3.2-1B-Instruct. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: Embeddings 1/1, Norms 7/33, MLP 48/48, Attention 64/64
3 derivatives checked
- mradermacher/Rombo-LLM-V2.7-llama-3.2-1b-i1-GGUF: Quantization
- mradermacher/Rombo-LLM-V2.7-llama-3.2-1b-GGUF: Same weights, converted
- Novaciano/Rombo-V2.7-L3.2-1b_Eroticquant3-GGUF: Quantization