Text Generation
Transformers
English
phi3
finance
entity-extraction
ner
phi-3
production
indian-banking
custom_code
4-bit precision
Instructions to use Ranjit0034/finance-entity-extractor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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) - 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
| """ | |
| Model Fusion Script. | |
| Fuses the domain-pretrained adapters into the base model to create | |
| a standalone finance-native base model. This model can then be | |
| fine-tuned for specific tasks. | |
| Author: Ranjit Behera | |
| """ | |
| import subprocess | |
| import argparse | |
| from pathlib import Path | |
| def fuse_model(base_model: str, adapter_path: str, output_path: str): | |
| """Run mlx_lm.fuse to merge adapters into base model.""" | |
| print(f"Merging {adapter_path} into {base_model}...") | |
| cmd = [ | |
| "mlx_lm.fuse", | |
| "--model", base_model, | |
| "--adapter-path", adapter_path, | |
| "--save-path", output_path | |
| ] | |
| try: | |
| subprocess.run(cmd, check=True) | |
| print(f"✅ Successfully fused model to {output_path}") | |
| except subprocess.CalledProcessError as e: | |
| print(f"❌ Fusion failed: {e}") | |
| if __name__ == "__main__": | |
| parser = argparse.ArgumentParser(description="Fuse MLX adapters into base model") | |
| parser.add_argument("--base", default="models/base/phi3-mini", help="Path to base model") | |
| parser.add_argument("--adapter", default="models/domain-pretrained/phi3-finance", help="Path to adapters") | |
| parser.add_argument("--output", default="models/base/phi3-finance-base", help="Output path for fused model") | |
| args = parser.parse_args() | |
| fuse_model(args.base, args.adapter, args.output) | |