Instructions to use RayanNan/Mistralsentiment with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RayanNan/Mistralsentiment with Transformers:

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

pipe = pipeline("text-generation", model="RayanNan/Mistralsentiment")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RayanNan/Mistralsentiment")
model = AutoModelForCausalLM.from_pretrained("RayanNan/Mistralsentiment")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RayanNan/Mistralsentiment with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/RayanNan/Mistralsentiment

SGLang

How to use RayanNan/Mistralsentiment 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 "RayanNan/Mistralsentiment" \
    --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": "RayanNan/Mistralsentiment",
		"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 "RayanNan/Mistralsentiment" \
        --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": "RayanNan/Mistralsentiment",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RayanNan/Mistralsentiment with Docker Model Runner:
```
docker model run hf.co/RayanNan/Mistralsentiment
```

Model Description

This model is trained basing on Mistral, which is used to detect sentiment of social media.

Author and their Hugging Face Account: Nan Ye(RayanNan), Zhen Ma(Mark01927), Chi Zhang(BillZhang0325), Jiayin Li(Moriacrafter)
Funded by: WenZhou Kean University
Model type: LLM
Language(s): English
Finetuned from model: e5-mistral-7b-instruct

Bias, Risks, and Limitations

The model we used to finetune the model is only considered about the Positive and Negative sentiment, the netural sentiment is not included

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

Training Details

Training Data

the model is trained basing on our own dataset with the link: RayanNan/Sentimentanalysis-endangeredspecies

Downloads last month: 4

Safetensors

Model size

7B params

Tensor type

F16

RayanNan
/

Mistralsentiment

Model Description

Bias, Risks, and Limitations

Recommendations

Training Details

Training Data

Dataset used to train RayanNan/Mistralsentiment