Instructions to use prometheus-eval/prometheus-7b-v1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prometheus-eval/prometheus-7b-v1.0 with Transformers:

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

pipe = pipeline("text-generation", model="prometheus-eval/prometheus-7b-v1.0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("prometheus-eval/prometheus-7b-v1.0")
model = AutoModelForCausalLM.from_pretrained("prometheus-eval/prometheus-7b-v1.0")

Inference
Local Apps Settings

vLLM

How to use prometheus-eval/prometheus-7b-v1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prometheus-eval/prometheus-7b-v1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prometheus-eval/prometheus-7b-v1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/prometheus-eval/prometheus-7b-v1.0

SGLang

How to use prometheus-eval/prometheus-7b-v1.0 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 "prometheus-eval/prometheus-7b-v1.0" \
    --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": "prometheus-eval/prometheus-7b-v1.0",
		"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 "prometheus-eval/prometheus-7b-v1.0" \
        --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": "prometheus-eval/prometheus-7b-v1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use prometheus-eval/prometheus-7b-v1.0 with Docker Model Runner:
```
docker model run hf.co/prometheus-eval/prometheus-7b-v1.0
```

seungone commited on Oct 14, 2023

Commit

e7fc9f2

1 Parent(s): 97c4509

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -1

README.md CHANGED Viewed

@@ -13,7 +13,12 @@ metrics:
 - spearmanr
 - accuracy
 ---
-- **Point of Contact:seungone@kaist.ac.kr**
 # TL;DR
 Prometheus is an alternative of GPT-4 evaluation when doing fine-grained evaluation of an underlying LLM & a Reward model for Reinforcement Learning from Human Feedback (RLHF).

 - spearmanr
 - accuracy
 ---
+## Links for Reference
+- **Homepage:https://github.com/kaistAI/Prometheus**
+- **Repository:https://github.com/kaistAI/Prometheus**
+- **Paper:https://arxiv.org/abs/2310.08491**
+- **Point of Contact:seungone@kaist.ac.kr**
 # TL;DR
 Prometheus is an alternative of GPT-4 evaluation when doing fine-grained evaluation of an underlying LLM & a Reward model for Reinforcement Learning from Human Feedback (RLHF).