automerger/Experiment28Yam-7B

Full fine-tune vs mayacinka/yam-jom-7B-slerp. 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

3 derivatives checked

• MaziyarPanahi/Experiment28Yam-7B-GGUF: Quantization
• mradermacher/Experiment28Yam-7B-GGUF: Same weights, converted
• MaziyarPanahi/NeuralsirkrishnaShadow_Experiment28Yam: Full fine-tune

On the Hub · Downloads on Model Pulse