kuotient/Llama-3-6B-Instruct-pruned

Partial fine-tune vs meta-llama/Meta-Llama-3-8B-Instruct. Partial change: 10% of the weights changed (attention, mlp, norms), in 3 of 24 layers.

Tensors changed: Embeddings 0/1, Norms 6/49, MLP 9/72, Attention 12/96, lm_head 0/1

1 derivatives checked

• mradermacher/Llama-3-6B-Instruct-pruned-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse