OmnicromsBrain/NeuralStar-7b-Lazy

Full fine-tune vs NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story. 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

3 derivatives checked

• mradermacher/NeuralStar-7b-Lazy-i1-GGUF: Quantization
• mradermacher/NeuralStar-7b-Lazy-GGUF: Same weights, converted
• OmnicromsBrain/NeuralStar_Story-9b: Full fine-tune (fewer layers)

On the Hub · Downloads on Model Pulse