Reinforcement Learning
Transformers
Safetensors
qwen3
text-generation
sdpo
srpo
ema
text-generation-inference
Instructions to use SeongryongJung/qwen3-8b-physics-srpo-ema005 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SeongryongJung/qwen3-8b-physics-srpo-ema005 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("SeongryongJung/qwen3-8b-physics-srpo-ema005") model = AutoModelForCausalLM.from_pretrained("SeongryongJung/qwen3-8b-physics-srpo-ema005", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download model-00004-of-00004.safetensors from SeongryongJung/qwen3-8b-physics-srpo-ema005: direct link, hf CLI and curl.
- Browser
- Download file 1.54 GB
-
https://huggingface.co/SeongryongJung/qwen3-8b-physics-srpo-ema005/resolve/main/model-00004-of-00004.safetensors
- Command line
-
hf download hf://SeongryongJung/qwen3-8b-physics-srpo-ema005/model-00004-of-00004.safetensors
-
curl -L -o model-00004-of-00004.safetensors https://huggingface.co/SeongryongJung/qwen3-8b-physics-srpo-ema005/resolve/main/model-00004-of-00004.safetensors
1.54 GB
- Xet hash:
- fed8eac0179f722154161a23e441e89c95d77cdfaab193038d25d9ae7ef9aa75
- Size of remote file:
- 1.54 GB
- SHA256:
- a6061983c333bc9ddce4c0e2a15f6291a855a7dea9e32599ea5a4043b6bb5fa6
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.