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

Libraries

How to use ishaansharma/llama_test_tiny_ola_hindi with Transformers:

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

pipe = pipeline("text-generation", model="ishaansharma/llama_test_tiny_ola_hindi")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ishaansharma/llama_test_tiny_ola_hindi")
model = AutoModelForCausalLM.from_pretrained("ishaansharma/llama_test_tiny_ola_hindi")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ishaansharma/llama_test_tiny_ola_hindi with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ishaansharma/llama_test_tiny_ola_hindi

SGLang

How to use ishaansharma/llama_test_tiny_ola_hindi 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 "ishaansharma/llama_test_tiny_ola_hindi" \
    --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": "ishaansharma/llama_test_tiny_ola_hindi",
		"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 "ishaansharma/llama_test_tiny_ola_hindi" \
        --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": "ishaansharma/llama_test_tiny_ola_hindi",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

This model is only for experimental purpose. This model was trained for very les duration with less computation power and was completed in less than 100 steps so please do not expect human like error less output. This is just an attempt to provide the POC and this model can be improved and trained further to be finetuned .

language: hi # <-- my language widget: - text: "मैं अपना किराया विवरण जांचना चाहता हूं" - text: "रद्दीकरण शुल्क क्यों लिया जाता है?" - text: "मैं रद्दीकरण शुल्क माफ़ी का अनुरोध कैसे कर सकता हूँ?" - text: "अग्रिम बुकिंग शुल्क क्या है?" - text: "मैं अपनी यात्रा पर कूपन कैसे लागू कर सकता हूँ?"

Downloads last month: -

ishaansharma
/

llama_test_tiny_ola_hindi

You need to agree to share your contact information to access this model

Spaces using ishaansharma/llama_test_tiny_ola_hindi 2