Instructions to use wenge-research/yayi-7b-llama2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wenge-research/yayi-7b-llama2 with Transformers:

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

pipe = pipeline("text-generation", model="wenge-research/yayi-7b-llama2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("wenge-research/yayi-7b-llama2")
model = AutoModelForCausalLM.from_pretrained("wenge-research/yayi-7b-llama2")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use wenge-research/yayi-7b-llama2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wenge-research/yayi-7b-llama2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wenge-research/yayi-7b-llama2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/wenge-research/yayi-7b-llama2

SGLang

How to use wenge-research/yayi-7b-llama2 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 "wenge-research/yayi-7b-llama2" \
    --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": "wenge-research/yayi-7b-llama2",
		"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 "wenge-research/yayi-7b-llama2" \
        --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": "wenge-research/yayi-7b-llama2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use wenge-research/yayi-7b-llama2 with Docker Model Runner:
```
docker model run hf.co/wenge-research/yayi-7b-llama2
```

how to load this model ?

by Maciel - opened Jul 23, 2023

Discussion

Maciel

Jul 23, 2023

RuntimeError: Failed to import transformers.models.llama.modeling_llama because of the following error (look up to see its traceback):
If you use @root_validator with pre=False (the default) you MUST specify skip_on_failure=True. Note that @root_validator is deprecated and should be replaced with @model_validator.
I have encountered this error.

Maciel

Jul 23, 2023

I have downgraded "pydantic" version to 1.10.9 and solved this problem.

wenge-research

Owner Jul 23, 2023

Thank you for your use. We will update the detailed usage methods next week, including the instruction formats and special tokens we use when training the model~

wenge-research changed discussion status to closed Jan 5, 2024

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

Tap or paste here to upload images

· Sign up or log in to comment