Instructions to use Hermi2023/doc2query-ppo-msmarco-100-121 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Hermi2023/doc2query-ppo-msmarco-100-121 with Transformers:

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

pipe = pipeline("text-generation", model="Hermi2023/doc2query-ppo-msmarco-100-121")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("Hermi2023/doc2query-ppo-msmarco-100-121")
model = AutoModelForSeq2SeqLM.from_pretrained("Hermi2023/doc2query-ppo-msmarco-100-121")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Hermi2023/doc2query-ppo-msmarco-100-121 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Hermi2023/doc2query-ppo-msmarco-100-121"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hermi2023/doc2query-ppo-msmarco-100-121",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Hermi2023/doc2query-ppo-msmarco-100-121

SGLang

How to use Hermi2023/doc2query-ppo-msmarco-100-121 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 "Hermi2023/doc2query-ppo-msmarco-100-121" \
    --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": "Hermi2023/doc2query-ppo-msmarco-100-121",
		"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 "Hermi2023/doc2query-ppo-msmarco-100-121" \
        --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": "Hermi2023/doc2query-ppo-msmarco-100-121",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Hermi2023/doc2query-ppo-msmarco-100-121 with Docker Model Runner:
```
docker model run hf.co/Hermi2023/doc2query-ppo-msmarco-100-121
```

Upload tokenizer

by Hermi2023 - opened Jul 31, 2023

base: refs/heads/main

←

from: refs/pr/5

Discussion Files changed

-0

Hermi2023

Owner Jul 31, 2023

No description provided.

Upload tokenizer7358f340

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment