Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

just1nseo
/
llama31-tulu3-8b-dpo-if-rlvr-constraint-only-kl0p05

Text Generation
Transformers
Safetensors
verl
grpo
rlvr
instruction-following
Model card Files Files and versions
xet
Community

Instructions to use just1nseo/llama31-tulu3-8b-dpo-if-rlvr-constraint-only-kl0p05 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use just1nseo/llama31-tulu3-8b-dpo-if-rlvr-constraint-only-kl0p05 with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("text-generation", model="just1nseo/llama31-tulu3-8b-dpo-if-rlvr-constraint-only-kl0p05")
    # pip install -U transformers accelerate
    # Load model directly
    from transformers import AutoModel
    model = AutoModel.from_pretrained("just1nseo/llama31-tulu3-8b-dpo-if-rlvr-constraint-only-kl0p05", device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps Settings
  • vLLM

    How to use just1nseo/llama31-tulu3-8b-dpo-if-rlvr-constraint-only-kl0p05 with vLLM:

    Install from pip and serve model
    # Install vLLM from pip:
    pip install vllm
    # Start the vLLM server:
    vllm serve "just1nseo/llama31-tulu3-8b-dpo-if-rlvr-constraint-only-kl0p05"
    # Call the server using curl (OpenAI-compatible API):
    curl -X POST "http://localhost:8000/v1/completions" \
    	-H "Content-Type: application/json" \
    	--data '{
    		"model": "just1nseo/llama31-tulu3-8b-dpo-if-rlvr-constraint-only-kl0p05",
    		"prompt": "Once upon a time,",
    		"max_tokens": 512,
    		"temperature": 0.5
    	}'
    Use Docker
    docker model run hf.co/just1nseo/llama31-tulu3-8b-dpo-if-rlvr-constraint-only-kl0p05
  • SGLang

    How to use just1nseo/llama31-tulu3-8b-dpo-if-rlvr-constraint-only-kl0p05 with SGLang:

    Install from pip and serve model
    # Install SGLang from pip:
    pip install sglang
    # Start the SGLang server:
    python3 -m sglang.launch_server \
        --model-path "just1nseo/llama31-tulu3-8b-dpo-if-rlvr-constraint-only-kl0p05" \
        --host 0.0.0.0 \
        --port 30000
    # Call the server using curl (OpenAI-compatible API):
    curl -X POST "http://localhost:30000/v1/completions" \
    	-H "Content-Type: application/json" \
    	--data '{
    		"model": "just1nseo/llama31-tulu3-8b-dpo-if-rlvr-constraint-only-kl0p05",
    		"prompt": "Once upon a time,",
    		"max_tokens": 512,
    		"temperature": 0.5
    	}'
    Use Docker images
    docker run --gpus all \
        --shm-size 32g \
        -p 30000:30000 \
        -v ~/.cache/huggingface:/root/.cache/huggingface \
        --env "HF_TOKEN=<secret>" \
        --ipc=host \
        lmsysorg/sglang:latest \
        python3 -m sglang.launch_server \
            --model-path "just1nseo/llama31-tulu3-8b-dpo-if-rlvr-constraint-only-kl0p05" \
            --host 0.0.0.0 \
            --port 30000
    # Call the server using curl (OpenAI-compatible API):
    curl -X POST "http://localhost:30000/v1/completions" \
    	-H "Content-Type: application/json" \
    	--data '{
    		"model": "just1nseo/llama31-tulu3-8b-dpo-if-rlvr-constraint-only-kl0p05",
    		"prompt": "Once upon a time,",
    		"max_tokens": 512,
    		"temperature": 0.5
    	}'
  • Docker Model Runner

    How to use just1nseo/llama31-tulu3-8b-dpo-if-rlvr-constraint-only-kl0p05 with Docker Model Runner:

    docker model run hf.co/just1nseo/llama31-tulu3-8b-dpo-if-rlvr-constraint-only-kl0p05
llama31-tulu3-8b-dpo-if-rlvr-constraint-only-kl0p05
129 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 6 commits
just1nseo's picture
just1nseo
llama31_tulu3_8b_dpo_grpo_nonthink_constraint_only_b1024_c1_kl0p05: global_step_364
4b9b8c8 verified 9 days ago
  • global_step_182
    llama31_tulu3_8b_dpo_grpo_nonthink_constraint_only_b1024_c1_kl0p05: global_step_182 10 days ago
  • global_step_273
    llama31_tulu3_8b_dpo_grpo_nonthink_constraint_only_b1024_c1_kl0p05: global_step_273 10 days ago
  • global_step_364
    llama31_tulu3_8b_dpo_grpo_nonthink_constraint_only_b1024_c1_kl0p05: global_step_364 9 days ago
  • global_step_91
    llama31_tulu3_8b_dpo_grpo_nonthink_constraint_only_b1024_c1_kl0p05: global_step_91 11 days ago
  • .gitattributes
    1.79 kB
    llama31_tulu3_8b_dpo_grpo_nonthink_constraint_only_b1024_c1_kl0p05: global_step_364 9 days ago
  • README.md
    920 Bytes
    Add run card 11 days ago