cstr/llama3-8b-spaetzle-v20
Full fine-tune vs nbeerbower/llama-3-wissenschaft-8B-v2. 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
- featherless-ai-quants/cstr-llama3-8b-spaetzle-v20-GGUF: Quantization
- cstr/llama3-8b-spaetzle-v33-mlx-4bit: Quantization
- mradermacher/llama3-8b-spaetzle-v20-GGUF: Same weights, converted
- cstr/llama3-8b-spaetzle-v33: Full fine-tune