ldsjmdy/Tulu3-SFT
Full fine-tune vs meta-llama/Llama-3.1-8B. 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
3 derivatives checked
- mradermacher/Tulu3-SFT-GGUF: Same weights, converted
- ldsjmdy/Tulu3-Block-FT: Full fine-tune
- ldsjmdy/Tulu3-RAG: Full fine-tune