cstr/llama3-8b-spaetzle-v33

Full fine-tune vs cstr/llama3-8b-spaetzle-v20. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

1 derivatives checked

• featherless-ai-quants/cstr-llama3-8b-spaetzle-v33-GGUF: Quantization

On the Hub · Downloads on Model Pulse