allenai/OLMo-2-0425-1B-Instruct
Full fine-tune vs allenai/OLMo-2-0425-1B-RLVR1. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, MLP 48/48, Norms 61/65, Attention 64/64
14 derivatives checked
- allenai/OLMo-2-0425-1B-Instruct-GGUF: Same weights, converted
- unsloth/OLMo-2-0425-1B-Instruct-GGUF: Same weights, converted
- daryaZare/iris-olmo-2-1b-combined-multihop-k2-ep4: Adapter
- daryaZare/iris-olmo-2-1b-combined-multihop-k5-ep4: Adapter
- mradermacher/OLMo-2-0425-1B-Instruct-i1-GGUF: Quantization
- unsloth/OLMo-2-0425-1B-Instruct: Identical copy
- arzaan789/olmo2-1b-uncensored: Partial fine-tune
- mradermacher/OLMo-2-0425-1B-Instruct-GGUF: Same weights, converted
- cx-cmu/repro-rephraser-1B: Full fine-tune
- DevQuasar/allenai.OLMo-2-0425-1B-Instruct-GGUF: Same weights, converted
- armandosds/OLMo-2-0425-1B-Instruct-GGUF: Same weights, converted
- Grogros/OLMo-2-0425-1B-Instruct-distillation-alpaca-5.0-AlpacaPoison: Full fine-tune
- jahyungu/OLMo-2-0425-1B-Instruct_gsm8k: Partial fine-tune
- Grogros/OLMo-2-0425-1B-Instruct-distillation-wildchat-alpaca-5.0-AlpacaPoison-4k: Full fine-tune
2 other repos hold byte-for-byte identical weight files.