Instructions to use ZebangCheng/Emotion-LLaMA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ZebangCheng/Emotion-LLaMA with Transformers:

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

pipe = pipeline("text-generation", model="ZebangCheng/Emotion-LLaMA")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ZebangCheng/Emotion-LLaMA")
model = AutoModelForCausalLM.from_pretrained("ZebangCheng/Emotion-LLaMA")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ZebangCheng/Emotion-LLaMA with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ZebangCheng/Emotion-LLaMA

SGLang

How to use ZebangCheng/Emotion-LLaMA 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 "ZebangCheng/Emotion-LLaMA" \
    --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": "ZebangCheng/Emotion-LLaMA",
		"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 "ZebangCheng/Emotion-LLaMA" \
        --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": "ZebangCheng/Emotion-LLaMA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ZebangCheng/Emotion-LLaMA with Docker Model Runner:
```
docker model run hf.co/ZebangCheng/Emotion-LLaMA
```

hi can i get the code for using this model ?

by sanak - opened Oct 26, 2024

Discussion

sanak

Oct 26, 2024

can i get code for using this model, alternative to the app version

ZebangCheng

Owner Oct 27, 2024

Yes, you can directly use this code, or you can refer to the local deployment tutorial on GitHub. Please make sure to comply with the relevant LICENSE when using it.

https://github.com/ZebangCheng/Emotion-LLaMA

fragrantly

Dec 15, 2024

How can I use this model to extract the embedding after the linear layer of the encoder? So how do I load this model weight and get the modules that I need? I didn't see those details on github.

ZebangCheng

Owner Dec 18, 2024

How can I use this model to extract the embedding after the linear layer of the encoder? So how do I load this model weight and get the modules that I need? I didn't see those details on github.

Hello, I suggest you open an issue on GitHub and describe your question in detail. I can provide a direct answer by referencing the code.

fragrantly

Dec 19, 2024

thanks for your answering!! I'll be asking you a question on github soon

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