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

Libraries

How to use bharatgenai/FinanceParam with Transformers:

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

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

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("bharatgenai/FinanceParam", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bharatgenai/FinanceParam with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/bharatgenai/FinanceParam

SGLang

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

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

kundeshwar20 commited on Feb 24

Commit

a9c652f

verified ·

1 Parent(s): 0da9055

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -6

README.md CHANGED Viewed

@@ -9,6 +9,7 @@ base_model:
 - bharatgenai/Param-1-2.9B-Instruct
 pipeline_tag: text-generation
 library_name: transformers
 ---
 <div align="center">
@@ -222,9 +223,4 @@ This table reports results by **question type** (e.g., MCQ, comprehension, reaso
 | Reading Comprehension    | 30.59         | 25.88                 | 31.76                 | 28.24              | 31.76                   | 30.59        |
 | Rearrange the sequence   | 24.29         | 23.59                 | 29.10                 | 28.39              | 22.88                   | 25.14        |
----
-## 📜 License
-This SFT checkpoint is released under the **BharatGen non-commercial license**.<br>
-Please refer to the [LICENSE](./LICENSE) for terms and conditions.

 - bharatgenai/Param-1-2.9B-Instruct
 pipeline_tag: text-generation
 library_name: transformers
+license: apache-2.0
 ---
 <div align="center">
 | Reading Comprehension    | 30.59         | 25.88                 | 31.76                 | 28.24              | 31.76                   | 30.59        |
 | Rearrange the sequence   | 24.29         | 23.59                 | 29.10                 | 28.39              | 22.88                   | 25.14        |
+---