OpenPipe/mistral-ft-optimized-1227
Full fine-tune vs Intel/neural-chat-7b-v3-3. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1
8 derivatives checked
- TheBloke/mistral-ft-optimized-1227-GGUF: Quantization
- mradermacher/mistral-ft-optimized-1227-i1-GGUF: Quantization
- MaziyarPanahi/mistral-ft-optimized-1227-GGUF: Quantization
- mradermacher/mistral-ft-optimized-1227-GGUF: Same weights, converted
- ichigoberry/MonarchPipe-7B-slerp: Full fine-tune
- MaziyarPanahi/NeuralPipe-7B-slerp-v0.2: Full fine-tune
- frost19k/dolphin-2.8-mistral-v02-2x7b: MoE built from dense models
- uproai/ros-7b-v1: Full fine-tune