ejbejaranos/Bitnet-Llama3-from8BM-now2B
Full fine-tune (fewer layers) vs meta-llama/Llama-3.1-8B-Instruct. ejbejaranos/Bitnet-Llama3-from8BM-now2B matches part of meta-llama/Llama-3.1-8B-Instruct (57 of its 291 tensors; the rest of meta-llama/Llama-3.1-8B-Instruct has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 6 of 6 layers.
Tensors changed: Embeddings 1/1, Norms 13/13, MLP 18/18, Attention 24/24, lm_head 1/1
1 derivatives checked
- mradermacher/Bitnet-Llama3-from8BM-now2B-GGUF: Full fine-tune