automerger/T3qm7xpT3q-7B

Full fine-tune vs chihoonlee10/T3Q-Mistral-Orca-Math-DPO. Fine-tune: 94% of the weights changed, across 31 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 18/65, MLP 90/96, Attention 120/128, lm_head 1/1

3 derivatives checked

• MaziyarPanahi/T3qm7xpT3q-7B-GGUF: Quantization
• MaziyarPanahi/YamshadowStrangemerges_32_T3qm7xpT3q: Full fine-tune
• MaziyarPanahi/YamshadowInex12_T3qm7xpT3q: Full fine-tune

On the Hub · Downloads on Model Pulse