allenai/OLMoE-1B-7B-0924-Instruct
Full fine-tune vs allenai/OLMoE-1B-7B-0924-SFT. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: Embeddings 1/1, Norms 48/65, MLP 2869/2869, Attention 64/64, lm_head 1/1
6 derivatives checked
- bartowski/OLMoE-1B-7B-0924-Instruct-GGUF: Same weights, converted
- mradermacher/OLMoE-1B-7B-0924-Instruct-i1-GGUF: Quantization
- mradermacher/OLMoE-1B-7B-0924-Instruct-GGUF: Same weights, converted
- allenai/OLMoE-1B-7B-0924-Instruct-GGUF: Same weights, converted
- DevQuasar-3/OLMoE-1B-7B-0924-Instruct-GGUF: Quantization
- armandosds/OLMoE-1B-7B-0924-Instruct-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.