Instructions to use microsoft/Sentiment-Analysis-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/Sentiment-Analysis-7B with Transformers:

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

pipe = pipeline("text-generation", model="microsoft/Sentiment-Analysis-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("microsoft/Sentiment-Analysis-7B")
model = AutoModelForCausalLM.from_pretrained("microsoft/Sentiment-Analysis-7B", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use microsoft/Sentiment-Analysis-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "microsoft/Sentiment-Analysis-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/Sentiment-Analysis-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/microsoft/Sentiment-Analysis-7B

SGLang

How to use microsoft/Sentiment-Analysis-7B 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 "microsoft/Sentiment-Analysis-7B" \
    --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": "microsoft/Sentiment-Analysis-7B",
		"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 "microsoft/Sentiment-Analysis-7B" \
        --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": "microsoft/Sentiment-Analysis-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use microsoft/Sentiment-Analysis-7B with Docker Model Runner:
```
docker model run hf.co/microsoft/Sentiment-Analysis-7B
```

AnuarSh commited on 3 days ago

Commit

c443f04

verified ·

1 Parent(s): a56b051

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -7

README.md CHANGED Viewed

@@ -15,7 +15,7 @@ tags:
 **Sentiment-Analysis-7B** is a 7B-parameter autoregressive language model fine-tuned for sentiment classification of user messages directed at a service, product, or agent (the "Target"). It is built on top of [*mistralai/Mistral-7B-Instruct-v0.2*](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) and was fine-tuned with reinforcement learning, using an LLM as a judge, on a small internal training set of ~300 examples. No pre-defined labels were used for training.
-Given a user message, the model generates a response in the following format: the **first token is the sentiment label** (`Negative`, `Neutral`, or `Positive`), followed by a short explanation of the decision. If only the label is needed, set `max_new_tokens=1`.
 ### Evaluation metrics
@@ -28,7 +28,7 @@ The evaluation metric used is accuracy. The following compares the base model wi
 ### How to use
-The model is a causal language model and is loaded with `AutoModelForCausalLM`. The sentiment label is always the first generated token, so setting `max_new_tokens=1` returns the label only. Use the system prompt below, which defines the "Target" and the sentiment rules.
 ```python
 import torch
@@ -67,7 +67,7 @@ inputs = tokenizer.apply_chat_template(
 ).to(model.device)
 # Label only
-output = model.generate(**inputs, max_new_tokens=1, do_sample=False)
 print(tokenizer.decode(output[0, inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
 ```
@@ -80,7 +80,7 @@ Negative
 To get the explanation as well, increase `max_new_tokens`:
 ```python
-output = model.generate(**inputs, max_new_tokens=128, do_sample=False)
 print(tokenizer.decode(output[0, inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
 ```
@@ -88,6 +88,4 @@ Output:
 ```
 Negative, the user states an inability to log in, which is a failure related to the Target.
-```
-> Created by Microsoft

 **Sentiment-Analysis-7B** is a 7B-parameter autoregressive language model fine-tuned for sentiment classification of user messages directed at a service, product, or agent (the "Target"). It is built on top of [*mistralai/Mistral-7B-Instruct-v0.2*](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) and was fine-tuned with reinforcement learning, using an LLM as a judge, on a small internal training set of ~300 examples. No pre-defined labels were used for training.
+Given a user message, the model generates a response in the following format: the **first token is the sentiment label** (`Negative`, `Neutral`, or `Positive`), followed by a short explanation of the decision. If only the label is needed, set `max_new_tokens=3`.
 ### Evaluation metrics
 ### How to use
+The model is a causal language model and is loaded with `AutoModelForCausalLM`. The sentiment label is always the first generated token, so setting `max_new_tokens=3` returns the label only. Use the system prompt below, which defines the "Target" and the sentiment rules.
 ```python
 import torch
 ).to(model.device)
 # Label only
+output = model.generate(**inputs, max_new_tokens=3, do_sample=False)
 print(tokenizer.decode(output[0, inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
 ```
 To get the explanation as well, increase `max_new_tokens`:
 ```python
+output = model.generate(**inputs, max_new_tokens=64, do_sample=False)
 print(tokenizer.decode(output[0, inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
 ```
 ```
 Negative, the user states an inability to log in, which is a failure related to the Target.
+```