nbeerbower/llama-3-bophades-v1-8B
Full fine-tune vs Azure99/blossom-v5-llama3-8b. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1
4 derivatives checked
- mradermacher/llama-3-bophades-v1-8B-i1-GGUF: Quantization
- mradermacher/llama-3-bophades-v1-8B-GGUF: Same weights, converted
- nbeerbower/llama-3-sauce-v2-8B: Full fine-tune
- nbeerbower/llama-3-sauce-v1-8B: LoRA-style