NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story
Full fine-tune vs mistralai/Mistral-7B-Instruct-v0.2. Fine-tune: 98% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 14/65, MLP 96/96, Attention 128/128, lm_head 1/1
5 derivatives checked
- mradermacher/Mistral-7B-Instruct-v0.2-Neural-Story-i1-GGUF: Quantization
- mradermacher/Mistral-7B-Instruct-v0.2-Neural-Story-GGUF: Same weights, converted
- jambroz/sixtyoneeighty-4x7B-v1: MoE built from dense models
- OmnicromsBrain/NeuralStar-7b-Lazy: Full fine-tune
- sixtyoneeighty/FNCARL9000: MoE built from dense models