Instructions to use sanjay734/sentiment-analyzer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sanjay734/sentiment-analyzer with Transformers:

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

pipe = pipeline("text-generation", model="sanjay734/sentiment-analyzer")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("sanjay734/sentiment-analyzer", device_map="auto")

PEFT
How to use sanjay734/sentiment-analyzer with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sanjay734/sentiment-analyzer with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sanjay734/sentiment-analyzer"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sanjay734/sentiment-analyzer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sanjay734/sentiment-analyzer

SGLang

How to use sanjay734/sentiment-analyzer 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 "sanjay734/sentiment-analyzer" \
    --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": "sanjay734/sentiment-analyzer",
		"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 "sanjay734/sentiment-analyzer" \
        --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": "sanjay734/sentiment-analyzer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sanjay734/sentiment-analyzer with Docker Model Runner:
```
docker model run hf.co/sanjay734/sentiment-analyzer
```

Sentiment Analyzer — Gemma 2B LoRA

A small sentiment-analysis fine-tune of Google's Gemma 2B model using LoRA (PEFT).

This model was fine-tuned by Sanjay734 and uploaded to Hugging Face as:

sanjay734/sentiment-analyzer

Model Details

Base model: google/gemma-2b
Fine-tuning method: LoRA / PEFT
Task: Sentiment classification
Sentiment labels: POSITIVE, NEGATIVE, NEUTRAL
Language: English
Author: Sanjay734
Hugging Face: sanjay734

Fine-Tuning Setup

The model was loaded in 4-bit quantization to reduce GPU memory usage.

LoRA Configuration

r = 8
lora_alpha = 16
lora_dropout = 0.05
task_type = CAUSAL_LM

Training Configuration

Batch size per device: 2
Maximum training steps: 50
Learning rate: 2e-4
Logging steps: 10
FP16: enabled

Training Data

The fine-tuning dataset contains 8 example reviews:

3 positive examples
3 negative examples
2 neutral examples

Example:

Review: I love this product!
Sentiment: POSITIVE

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for sanjay734/sentiment-analyzer

Base model

google/gemma-2b

Adapter

(23699)

this model