UNIVA-Bllossom/DeepSeek-llama3.3-Bllossom-70B
Full fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Llama-70B. Fine-tune: 99% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 0/1, Attention 320/320, MLP 240/240, Norms 134/161, lm_head 1/1
2 derivatives checked
- bartowski/UNIVA-Bllossom_DeepSeek-llama3.3-Bllossom-70B-GGUF: Full fine-tune
- mradermacher/DeepSeek-llama3.3-Bllossom-70B-GGUF: Full fine-tune
1 other repos hold byte-for-byte identical weight files.