Kukedlc/NeuralMaths-Experiment-7b
Full fine-tune vs Eric111/Mayo. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: MLP 96/96, Attention 128/128, Norms 65/65, Embeddings 1/1, lm_head 1/1
4 derivatives checked
- mradermacher/NeuralMaths-Experiment-7b-GGUF: Quantization
- featherless-ai-quants/Kukedlc-NeuralMaths-Experiment-7b-GGUF: Quantization
- Ppoyaa/Neural-AlphaMistral-7B: Full fine-tune
- Kukedlc/NeuralMathsRolePlay-7b: Full fine-tune