Instructions to use Ranjit0034/finance-entity-extractor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ranjit0034/finance-entity-extractor with Transformers:

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

pipe = pipeline("text-generation", model="Ranjit0034/finance-entity-extractor", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ranjit0034/finance-entity-extractor", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Ranjit0034/finance-entity-extractor", trust_remote_code=True)

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Ranjit0034/finance-entity-extractor with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ranjit0034/finance-entity-extractor"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ranjit0034/finance-entity-extractor",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Ranjit0034/finance-entity-extractor

SGLang

How to use Ranjit0034/finance-entity-extractor 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 "Ranjit0034/finance-entity-extractor" \
    --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": "Ranjit0034/finance-entity-extractor",
		"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 "Ranjit0034/finance-entity-extractor" \
        --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": "Ranjit0034/finance-entity-extractor",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Ranjit0034/finance-entity-extractor with Docker Model Runner:
```
docker model run hf.co/Ranjit0034/finance-entity-extractor
```

Ranjit Behera commited on Jan 10

Commit

c876830

1 Parent(s): 354e581

Fix: Default to regex-only mode for instant usage

Browse files

v1.0.2:
- use_llm defaults to False (no 5GB model download)
- Package works instantly out of the box
- Users can enable LLM with ExtractionConfig(use_llm=True)

Files changed (2) hide show

pyproject.toml +10 -3
src/finee/schema.py +1 -1

pyproject.toml CHANGED Viewed

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 [project]
 name = "finee"
-version = "1.0.0"
 description = "Extract structured financial entities from Indian banking messages"
 readme = "README.md"
 license = "MIT"
@@ -91,12 +91,19 @@ Issues = "https://github.com/Ranjit0034/llm-mail-trainer/issues"
 [project.scripts]
 finee = "finee.cli:main"
-[tool.hatch.build]
-packages = ["src/finee"]
 [tool.hatch.build.targets.wheel]
 packages = ["src/finee"]
 [tool.pytest.ini_options]
 testpaths = ["tests"]
 python_files = ["test_*.py"]

 [project]
 name = "finee"
+version = "1.0.2"
 description = "Extract structured financial entities from Indian banking messages"
 readme = "README.md"
 license = "MIT"
 [project.scripts]
 finee = "finee.cli:main"
+[tool.hatch.build.targets.sdist]
+include = [
+    "/src/finee",
+    "/README.md",
+    "/LICENSE",
+]
 [tool.hatch.build.targets.wheel]
 packages = ["src/finee"]
+[tool.hatch.build.targets.wheel.sources]
+"src" = ""
 [tool.pytest.ini_options]
 testpaths = ["tests"]
 python_files = ["test_*.py"]

src/finee/schema.py CHANGED Viewed

@@ -158,7 +158,7 @@ class ExtractionConfig:
     cache_max_size: int = 1000
     # LLM settings
-    use_llm: bool = True
     llm_timeout_seconds: float = 10.0
     llm_max_tokens: int = 200
     llm_temperature: float = 0.1

     cache_max_size: int = 1000
     # LLM settings
+    use_llm: bool = False  # Set to True to enable LLM (requires model download)
     llm_timeout_seconds: float = 10.0
     llm_max_tokens: int = 200
     llm_temperature: float = 0.1