Pomilon/LEMA-llama-2-7b

Full fine-tune vs NousResearch/Llama-2-7b-hf. Fine-tune: 96% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 20/65, MLP 96/96, Attention 128/128, lm_head 0/1

2 derivatives checked

• mradermacher/LEMA-llama-2-7b-i1-GGUF: Quantization
• mradermacher/LEMA-llama-2-7b-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse