Reinforcement Learning
Transformers
Safetensors
English
qwen3
text-generation
grpo
trl
structured-output
sft-to-grpo
text-generation-inference
4-bit precision
bitsandbytes
Instructions to use zerg2187/GRPO_structeval_t_qwen3_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zerg2187/GRPO_structeval_t_qwen3_v1 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("zerg2187/GRPO_structeval_t_qwen3_v1") model = AutoModelForCausalLM.from_pretrained("zerg2187/GRPO_structeval_t_qwen3_v1") - Notebooks
- Google Colab
- Kaggle
| { | |
| "do_sample": true, | |
| "eos_token_id": [ | |
| 151645, | |
| 151643 | |
| ], | |
| "max_length": 262144, | |
| "pad_token_id": 151643, | |
| "temperature": 0.7, | |
| "top_k": 20, | |
| "top_p": 0.8, | |
| "transformers_version": "4.56.2" | |
| } | |