SL-AI/GRaPE-Flash

Full fine-tune vs allenai/OLMoE-1B-7B-0125. Fine-tune: 98% of the weights changed, across 16 of 16 layers.

Tensors changed: Embeddings 0/1, Norms 65/65, MLP 2869/2869, Attention 64/64, lm_head 1/1

2 derivatives checked

• mradermacher/GRaPE-Flash-i1-GGUF: Quantization
• mradermacher/GRaPE-Flash-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse