Reinforcement Learning
Transformers
Safetensors
olmo2
text-generation
rlvr
rl-zero
chain-of-thought
faithfulness
reward-hacking
cue-injection
unfaithrl
Instructions to use UnfaithRL/OLMo-2-0425-1B-hybrid_accuracy_hint_reward-512 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UnfaithRL/OLMo-2-0425-1B-hybrid_accuracy_hint_reward-512 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("UnfaithRL/OLMo-2-0425-1B-hybrid_accuracy_hint_reward-512") model = AutoModelForCausalLM.from_pretrained("UnfaithRL/OLMo-2-0425-1B-hybrid_accuracy_hint_reward-512", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download model-00002-of-00002.safetensors from UnfaithRL/OLMo-2-0425-1B-hybrid_accuracy_hint_reward-512: direct link, hf CLI and curl.
- Browser
- Download file 956 MB
-
https://huggingface.co/UnfaithRL/OLMo-2-0425-1B-hybrid_accuracy_hint_reward-512/resolve/main/model-00002-of-00002.safetensors
- Command line
-
hf download hf://UnfaithRL/OLMo-2-0425-1B-hybrid_accuracy_hint_reward-512/model-00002-of-00002.safetensors
-
curl -L -o model-00002-of-00002.safetensors https://huggingface.co/UnfaithRL/OLMo-2-0425-1B-hybrid_accuracy_hint_reward-512/resolve/main/model-00002-of-00002.safetensors
956 MB
- Xet hash:
- bb45bff2b6f530953f4b0d7475821a4f20e0e46f7ef8b9f94bb51fceebc095ea
- Size of remote file:
- 956 MB
- SHA256:
- 56ada4bb05608669f14b5b4b7742504f2514ab3c573f97abdb9e65176c7a8f55
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.