Instructions to use Udith-Sandaruwan/Llama-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Udith-Sandaruwan/Llama-test with Transformers:

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

pipe = pipeline("text-generation", model="Udith-Sandaruwan/Llama-test")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Udith-Sandaruwan/Llama-test")
model = AutoModelForCausalLM.from_pretrained("Udith-Sandaruwan/Llama-test")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Udith-Sandaruwan/Llama-test with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Udith-Sandaruwan/Llama-test

SGLang

How to use Udith-Sandaruwan/Llama-test 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 "Udith-Sandaruwan/Llama-test" \
    --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": "Udith-Sandaruwan/Llama-test",
		"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 "Udith-Sandaruwan/Llama-test" \
        --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": "Udith-Sandaruwan/Llama-test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Udith-Sandaruwan/Llama-test with Docker Model Runner:
```
docker model run hf.co/Udith-Sandaruwan/Llama-test
```

Udith-Sandaruwan commited on Feb 6, 2025

Commit

d1d9162

verified ·

1 Parent(s): 64c1e3a

Checkpoint @ step 5

Browse files

Files changed (1) hide show

checkpoints/checkpoint-5/tokenizer.json +2 -2

checkpoints/checkpoint-5/tokenizer.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9d4fd2d4afa82d8a7dadae3490fdc20b26f06e32cec78a8dc96521b4dc79038
-size 17210200

 version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920