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-1024 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-1024 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("UnfaithRL/OLMo-2-0425-1B-hybrid_accuracy_hint_reward-1024") model = AutoModelForCausalLM.from_pretrained("UnfaithRL/OLMo-2-0425-1B-hybrid_accuracy_hint_reward-1024", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download model-00001-of-00002.safetensors from UnfaithRL/OLMo-2-0425-1B-hybrid_accuracy_hint_reward-1024: direct link, hf CLI and curl.
- Browser
- Download file 4.98 GB
-
https://huggingface.co/UnfaithRL/OLMo-2-0425-1B-hybrid_accuracy_hint_reward-1024/resolve/main/model-00001-of-00002.safetensors
- Command line
-
hf download hf://UnfaithRL/OLMo-2-0425-1B-hybrid_accuracy_hint_reward-1024/model-00001-of-00002.safetensors
-
curl -L -o model-00001-of-00002.safetensors https://huggingface.co/UnfaithRL/OLMo-2-0425-1B-hybrid_accuracy_hint_reward-1024/resolve/main/model-00001-of-00002.safetensors
4.98 GB
- Xet hash:
- 4e17015b33d24d08a138558a701a25d0db78ea32c6c2ab0765a5d0f2e9db8cbb
- Size of remote file:
- 4.98 GB
- SHA256:
- eee5183d975f5fc0e64867ca25f7c52a696c5ddd6d78e8ea459e0de80fec07ab
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.