Reinforcement Learning
Transformers
Safetensors
qwen2
text-generation
rlvr
rl-zero
chain-of-thought
faithfulness
reward-hacking
cue-injection
unfaithrl
text-generation-inference
Instructions to use UnfaithRL/Qwen2.5-0.5B-Instruct-mmlu_trained_ha-1024 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UnfaithRL/Qwen2.5-0.5B-Instruct-mmlu_trained_ha-1024 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("UnfaithRL/Qwen2.5-0.5B-Instruct-mmlu_trained_ha-1024") model = AutoModelForCausalLM.from_pretrained("UnfaithRL/Qwen2.5-0.5B-Instruct-mmlu_trained_ha-1024", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 216 Bytes
14a031a | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 | {
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8,
"transformers_version": "4.56.1"
}
|