Kukedlc/NeuralSynthesis-7b-v0.4-slerp
Full fine-tune vs Kukedlc/NeuralSynthesis-7B-v0.1. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 93/96, Attention 124/128, lm_head 1/1
6 derivatives checked
- mradermacher/NeuralSynthesis-7b-v0.4-slerp-i1-GGUF: Quantization
- mradermacher/NeuralSynthesis-7b-v0.4-slerp-GGUF: Same weights, converted
- featherless-ai-quants/Kukedlc-NeuralSynthesis-7b-v0.4-slerp-GGUF: Quantization
- tensorblock/NeuralSynthesis-7b-v0.4-slerp-GGUF: Quantization
- automerger/T3qm7xpNeuralsynthesis-7B: Full fine-tune
- automerger/NeuralsynthesisT3qm7-7B: Full fine-tune
1 other repos hold byte-for-byte identical weight files.