MaziyarPanahi/Mistral-7B-Instruct-KhanAcademy-v0.2
Full fine-tune vs mistralai/Mistral-7B-Instruct-v0.2. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 13/65, MLP 96/96, Attention 128/128, lm_head 1/1
3 derivatives checked
- mradermacher/Mistral-7B-Instruct-KhanAcademy-v0.2-i1-GGUF: Quantization
- MaziyarPanahi/Mistral-7B-Instruct-KhanAcademy-v0.2-GGUF: Quantization
- mradermacher/Mistral-7B-Instruct-KhanAcademy-v0.2-GGUF: Same weights, converted