We lifted 1 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| allenai/OLMoE | canonical | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| set_args_for_val | Ran | allenai/OLMoE/scripts/eval_openlm_ckpt.py code served (permissive licence) · get_code("e67c82963b22e823") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We introduce OLMoE, a fully open, state-of-the-art language model leveraging sparse Mixture-of-Experts (MoE). OLMoE-1B-7B has 7 billion (B) parameters but uses only 1B per input token. We pretrain it on 5 trillion tokens and further adapt it to create OLMoE-1B-7B-Instruct. Our models outperform all available models with similar active parameters, even surpassing larger ones like Llama2-13B-Chat and DeepSeekMoE-16B. We present various experiments on MoE training, analyze routing in our model showing high specialization, and open-source all aspects of our work: model weights, training data, code, and logs.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2409.02060")
get_code_for_paper("2409.02060")
have("2409.02060")
Connect an agent — have() is free.