Instructions to use williyam/agentic-rag-aerospace-grpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use williyam/agentic-rag-aerospace-grpo with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct")
model = PeftModel.from_pretrained(base_model, "williyam/agentic-rag-aerospace-grpo")

Transformers

How to use williyam/agentic-rag-aerospace-grpo with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="williyam/agentic-rag-aerospace-grpo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("williyam/agentic-rag-aerospace-grpo", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use williyam/agentic-rag-aerospace-grpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "williyam/agentic-rag-aerospace-grpo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "williyam/agentic-rag-aerospace-grpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/williyam/agentic-rag-aerospace-grpo

SGLang

How to use williyam/agentic-rag-aerospace-grpo 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 "williyam/agentic-rag-aerospace-grpo" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "williyam/agentic-rag-aerospace-grpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "williyam/agentic-rag-aerospace-grpo" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "williyam/agentic-rag-aerospace-grpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use williyam/agentic-rag-aerospace-grpo with Docker Model Runner:
```
docker model run hf.co/williyam/agentic-rag-aerospace-grpo
```

williyam commited on 22 days ago

Commit

7932603

1 Parent(s): b239b93

chore: remove rag-8000.zcodecorp.in live link and hackathon text

Browse files

Files changed (1) hide show

README.md +0 -2

README.md CHANGED Viewed

@@ -160,7 +160,6 @@ This model is designed for **agentic RAG tasks in aerospace research**. It's tra
 | **GitHub Repository** | [agentic-rag-gym](https://github.com/williyam-m/agentic-rag-gym) |
 | **Training Notebook** | [Google Colab](https://colab.research.google.com/drive/14il2JQmy9-id_fSGpmYbssp-j975DSDo?usp=sharing) |
 | **Base Model** | [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) |
-| **Agentic RAG OS** | [Live Platform](https://rag-8000.zcodecorp.in/) |
 ## Citation
@@ -173,4 +172,3 @@ This model is designed for **agentic RAG tasks in aerospace research**. It's tra
 }
 ```
-*Built for the Meta × OpenEnv × Hugging Face × PyTorch Hackathon*

 | **GitHub Repository** | [agentic-rag-gym](https://github.com/williyam-m/agentic-rag-gym) |
 | **Training Notebook** | [Google Colab](https://colab.research.google.com/drive/14il2JQmy9-id_fSGpmYbssp-j975DSDo?usp=sharing) |
 | **Base Model** | [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) |
 ## Citation
 }
 ```