Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

Pratyush-01
/
physix-3b-rl-ckpt

Transformers
Safetensors
Generated from Trainer
hf_jobs
trl
grpo
unsloth
Model card Files Files and versions
xet
Community

Instructions to use Pratyush-01/physix-3b-rl-ckpt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use Pratyush-01/physix-3b-rl-ckpt with Transformers:

    # Load model directly
    from transformers import AutoModel
    model = AutoModel.from_pretrained("Pratyush-01/physix-3b-rl-ckpt", dtype="auto")
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps
  • Unsloth Studio new

    How to use Pratyush-01/physix-3b-rl-ckpt with Unsloth Studio:

    Install Unsloth Studio (macOS, Linux, WSL)
    curl -fsSL https://unsloth.ai/install.sh | sh
    # Run unsloth studio
    unsloth studio -H 0.0.0.0 -p 8888
    # Then open http://localhost:8888 in your browser
    # Search for Pratyush-01/physix-3b-rl-ckpt to start chatting
    Install Unsloth Studio (Windows)
    irm https://unsloth.ai/install.ps1 | iex
    # Run unsloth studio
    unsloth studio -H 0.0.0.0 -p 8888
    # Then open http://localhost:8888 in your browser
    # Search for Pratyush-01/physix-3b-rl-ckpt to start chatting
    Using HuggingFace Spaces for Unsloth
    # No setup required
    # Open https://huggingface.co/spaces/unsloth/studio in your browser
    # Search for Pratyush-01/physix-3b-rl-ckpt to start chatting
    Load model with FastModel
    pip install unsloth
    from unsloth import FastModel
    model, tokenizer = FastModel.from_pretrained(
        model_name="Pratyush-01/physix-3b-rl-ckpt",
        max_seq_length=2048,
    )
physix-3b-rl-ckpt / sft
Ctrl+K
Ctrl+K
  • 1 contributor
History: 5 commits
Pratyush-01's picture
Pratyush-01
SFT merged_16bit: Qwen/Qwen2.5-3B-Instruct | epochs=4 lora_r=32
8424cdf verified 12 days ago
  • added_tokens.json
    632 Bytes
    SFT merged_16bit: Qwen/Qwen2.5-3B-Instruct | epochs=3 lora_r=32 12 days ago
  • chat_template.jinja
    2.51 kB
    SFT merged_16bit: Qwen/Qwen2.5-3B-Instruct | epochs=3 lora_r=32 12 days ago
  • config.json
    1.72 kB
    SFT merged_16bit: Qwen/Qwen2.5-3B-Instruct | epochs=3 lora_r=32 12 days ago
  • merges.txt
    1.67 MB
    SFT merged_16bit: Qwen/Qwen2.5-3B-Instruct | epochs=3 lora_r=32 12 days ago
  • model-00001-of-00002.safetensors
    3.97 GB
    xet
    SFT merged_16bit: Qwen/Qwen2.5-3B-Instruct | epochs=4 lora_r=32 12 days ago
  • model-00002-of-00002.safetensors
    2.2 GB
    xet
    SFT merged_16bit: Qwen/Qwen2.5-3B-Instruct | epochs=4 lora_r=32 12 days ago
  • model.safetensors.index.json
    35.6 kB
    SFT merged_16bit: Qwen/Qwen2.5-3B-Instruct | epochs=3 lora_r=32 12 days ago
  • special_tokens_map.json
    499 Bytes
    SFT merged_16bit: Qwen/Qwen2.5-3B-Instruct | epochs=3 lora_r=32 12 days ago
  • tokenizer.json
    11.4 MB
    xet
    SFT merged_16bit: Qwen/Qwen2.5-3B-Instruct | epochs=3 lora_r=32 12 days ago
  • tokenizer_config.json
    7.54 kB
    SFT merged_16bit: Qwen/Qwen2.5-3B-Instruct | epochs=3 lora_r=32 12 days ago
  • vocab.json
    2.78 MB
    SFT merged_16bit: Qwen/Qwen2.5-3B-Instruct | epochs=3 lora_r=32 12 days ago