automerger/Experiment28T3q-7B
Full fine-tune vs chihoonlee10/T3Q-Mistral-Orca-Math-DPO. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1
12 derivatives checked
- MaziyarPanahi/Experiment28T3q-7B-GGUF: Quantization
- MaziyarPanahi/Experiment28T3q_Strangemerges_32Yam: Full fine-tune
- MaziyarPanahi/Experiment28T3q_Experiment29Multi_verse_model: Full fine-tune
- MaziyarPanahi/M7Yamshadowexperiment28_Experiment28T3q: Full fine-tune
- MaziyarPanahi/Experiment28T3q_Strangemerges_32Experiment28: Full fine-tune
- MaziyarPanahi/Experiment28T3q_Inex12Experiment28: Full fine-tune
- MaziyarPanahi/Experiment28T3q_PasticheAlloyingotneoy: Full fine-tune
- MaziyarPanahi/Experiment28T3q_OgnoPastiche: Full fine-tune
- MaziyarPanahi/Experiment28T3q_Strangemerges_30Experiment28: Full fine-tune
- MaziyarPanahi/Experiment28T3q_Strangemerges_32Ogno: Full fine-tune
- MaziyarPanahi/Experiment28T3q_Ognoexperiment27M7: Full fine-tune
- MaziyarPanahi/Experiment28T3q_Strangemerges_30Experiment26: Full fine-tune