Instructions to use Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0 with Transformers:

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

pipe = pipeline("text-generation", model="Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0")
model = AutoModelForCausalLM.from_pretrained("Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0

SGLang

How to use Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0 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 "Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0" \
    --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": "Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0",
		"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 "Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0" \
        --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": "Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0 with Docker Model Runner:
```
docker model run hf.co/Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0
```

Telugu-LLM-Labs

ravithejads commited on Mar 20, 2024

Commit

90c88db

verified ·

1 Parent(s): 0218dec

Update README.md (#1)

Browse files

- Update README.md (d9d4a224b1d6ebe75555e4e7c2bf6311d1f730bc)

Co-authored-by: Ravi Theja <ravithejads@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +1 -2

README.md CHANGED Viewed

@@ -128,8 +128,7 @@ response = tokenizer.batch_decode(outputs)
 # Inference with HuggingFace
 ```python3
-from peft import AutoModelForCausalLM
-from transformers import AutoTokenizer
 import torch
 model = AutoModelForCausalLM.from_pretrained(

 # Inference with HuggingFace
 ```python3
+from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 model = AutoModelForCausalLM.from_pretrained(