cstr/llama3.1-8b-spaetzle-v74
Full fine-tune vs cstr/llama3.1-8b-spaetzle-v59. 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
3 derivatives checked
- featherless-ai-quants/cstr-llama3.1-8b-spaetzle-v74-GGUF: Quantization
- mradermacher/llama3.1-8b-spaetzle-v74-GGUF: Same weights, converted
- cstr/llama3.1-8b-spaetzle-v90: Full fine-tune