BEE-spoke-data/Meta-Llama-3-8Bee

Full fine-tune vs meta-llama/Meta-Llama-3-8B. Fine-tune: 93% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 15/65, MLP 96/96, Attention 128/128, lm_head 1/1

3 derivatives checked

• mradermacher/Meta-Llama-3-8Bee-i1-GGUF: Quantization
• mradermacher/Meta-Llama-3-8Bee-GGUF: Same weights, converted
• afrideva/Meta-Llama-3-8Bee-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse