empirischtech/Llama-3.1-10B-Instruct

Partial fine-tune vs meta-llama/Llama-3.1-8B-Instruct. Partial change: 30% of the weights changed (attention, mlp, norms), in 11 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 22/65, MLP 33/96, Attention 44/128, lm_head 0/1

2 derivatives checked

• mradermacher/Llama-3.1-10B-Instruct-i1-GGUF: Quantization
• mradermacher/Llama-3.1-10B-Instruct-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse