castorini/rank_zephyr_7b_v1_full
Full fine-tune vs mistralai/Mistral-7B-v0.1. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 33/65, MLP 96/96, Attention 128/128, lm_head 1/1
3 derivatives checked
- MaziyarPanahi/rank_zephyr_7b_v1_full-GGUF: Quantization
- tinyopsec/rank-zephyr-7b-v1-full-GGUF: Same weights, converted
- tensorblock/rank_zephyr_7b_v1_full-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.