openchat/openchat-3.5-1210
Full fine-tune vs mistralai/Mistral-7B-v0.1. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128
5 derivatives checked
- TheBloke/openchat-3.5-1210-GGUF: Quantization
- mradermacher/openchat-3.5-1210-i1-GGUF: Quantization
- MaziyarPanahi/openchat-3.5-1210-GGUF: Quantization
- mradermacher/openchat-3.5-1210-GGUF: Same weights, converted
- second-state/openchat-3.5-1210-GGUF: Quantization
4 other repos hold byte-for-byte identical weight files.