Instructions to use OdiaGenAI/odiagenAI-bengali-base-model-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OdiaGenAI/odiagenAI-bengali-base-model-v1 with Transformers:

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

pipe = pipeline("text-generation", model="OdiaGenAI/odiagenAI-bengali-base-model-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OdiaGenAI/odiagenAI-bengali-base-model-v1")
model = AutoModelForCausalLM.from_pretrained("OdiaGenAI/odiagenAI-bengali-base-model-v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OdiaGenAI/odiagenAI-bengali-base-model-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/OdiaGenAI/odiagenAI-bengali-base-model-v1

SGLang

How to use OdiaGenAI/odiagenAI-bengali-base-model-v1 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 "OdiaGenAI/odiagenAI-bengali-base-model-v1" \
    --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": "OdiaGenAI/odiagenAI-bengali-base-model-v1",
		"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 "OdiaGenAI/odiagenAI-bengali-base-model-v1" \
        --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": "OdiaGenAI/odiagenAI-bengali-base-model-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OdiaGenAI/odiagenAI-bengali-base-model-v1 with Docker Model Runner:
```
docker model run hf.co/OdiaGenAI/odiagenAI-bengali-base-model-v1
```

Model Card for Model ID

Model description

odiagenAI-bengali-base-model-v1 is based on Llama-7b and finetuned with 252k Bengali instruction set. The instruction set is translated data from open-source resources, resulting in good Bengali instruction understanding and response generation capabilities.

The code of Bengali data generation and other detailed information can be found in our Github project repository: https://github.com/OdiaGenAI/GenerativeAI_and_LLM_Odia.

Training hyper-parameters

Parameter	Value
Batch size	128
Learning rate	3e-4
Epochs	5
Cutoff length	256
Weight_decay	0.001
Warmup_rate	0.1
LR_scheduler	linear
Lora r	16
Lora target modules	(q_proj, k_proj, v_proj, o_proj)

Instructions for running it can be found at https://github.com/OdiaGenAI/GenerativeAI_and_LLM_Odia.

Licensing Information

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Citation Information

If you find this helpful repository, please consider giving 👏 and citing:

@misc{OdiaGenAI-Bengali-LLM,
  author = {Shantipriya Parida and Sambit Sekhar and Guneet Singh Kohli and Arghyadeep Sen and Shashikanta Sahoo},
  title = {Bengali Instruction-Tuning Model},
  year = {2023},
  publisher = {Hugging Face},
  journal = {Hugging Face repository},
  howpublished = {\url{https://huggingface.co/OdiaGenAI}},
}

Contributions

Shantipriya Parida
Sambit Sekhar
Guneet Singh Kohli
Arghyadeep Sen
Shashikanta Sahoo

Downloads last month: 9