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 tokenizer.json from UnfaithRL/OLMo-2-0425-1B-hybrid_accuracy_hint_reward-512: direct link, hf CLI and curl.
- Browser
- Download file 7.14 MB
-
https://huggingface.co/UnfaithRL/OLMo-2-0425-1B-hybrid_accuracy_hint_reward-512/resolve/main/tokenizer.json
- Command line
-
hf download hf://UnfaithRL/OLMo-2-0425-1B-hybrid_accuracy_hint_reward-512/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/UnfaithRL/OLMo-2-0425-1B-hybrid_accuracy_hint_reward-512/resolve/main/tokenizer.json
7.14 MB
File too large to display, you can check the raw version instead.