sail/Sailor-7B-Chat
Full fine-tune vs sail/Sailor-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 42/65, MLP 96/96, Attention 224/224
2 derivatives checked
- mradermacher/Sailor-7B-Chat-GGUF: Same weights, converted
- tensorblock/Sailor-7B-Chat-GGUF: Quantization