Instructions to use microsoft/LLaMA-2-13b-GTL-Delta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/LLaMA-2-13b-GTL-Delta with Transformers:

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

pipe = pipeline("text-generation", model="microsoft/LLaMA-2-13b-GTL-Delta")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("microsoft/LLaMA-2-13b-GTL-Delta")
model = AutoModelForCausalLM.from_pretrained("microsoft/LLaMA-2-13b-GTL-Delta", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use microsoft/LLaMA-2-13b-GTL-Delta with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "microsoft/LLaMA-2-13b-GTL-Delta"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/LLaMA-2-13b-GTL-Delta",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/microsoft/LLaMA-2-13b-GTL-Delta

SGLang

How to use microsoft/LLaMA-2-13b-GTL-Delta 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 "microsoft/LLaMA-2-13b-GTL-Delta" \
    --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": "microsoft/LLaMA-2-13b-GTL-Delta",
		"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 "microsoft/LLaMA-2-13b-GTL-Delta" \
        --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": "microsoft/LLaMA-2-13b-GTL-Delta",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use microsoft/LLaMA-2-13b-GTL-Delta with Docker Model Runner:
```
docker model run hf.co/microsoft/LLaMA-2-13b-GTL-Delta
```

XumengWen commited on Aug 12, 2024

Commit

13c993d

1 Parent(s): 78df23b

update quickstart

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -104,8 +104,8 @@ with open(example_path, "r") as f:
     full_prompt = f.read()
 answer = full_prompt.split('Answer:')[-1].strip()
 prompt_without_answer = full_prompt[:-len(answer)]
-print("Prompt:\n", prompt_without_answer)
-print("Label:", answer)
 # Inference
 inputs = tokenizer(prompt_without_answer, return_tensors="pt")
@@ -118,7 +118,7 @@ outputs = model.generate(
 )
 # Print the answer
-print("Generate answer:", tokenizer.decode(outputs[0][input_ids.shape[-1]:]))
 ```
 ## Responsible AI Considerations

     full_prompt = f.read()
 answer = full_prompt.split('Answer:')[-1].strip()
 prompt_without_answer = full_prompt[:-len(answer)]
+print("Prompt:", prompt_without_answer)
+print("Groundtruth:", answer)
 # Inference
 inputs = tokenizer(prompt_without_answer, return_tensors="pt")
 )
 # Print the answer
+print("Generated answer:", tokenizer.decode(outputs[0][input_ids.shape[-1]:]))
 ```
 ## Responsible AI Considerations