Instructions to use h2oai/llama2-0b-unit-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use h2oai/llama2-0b-unit-test with Transformers:

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

pipe = pipeline("text-generation", model="h2oai/llama2-0b-unit-test")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("h2oai/llama2-0b-unit-test")
model = AutoModelForCausalLM.from_pretrained("h2oai/llama2-0b-unit-test")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use h2oai/llama2-0b-unit-test with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "h2oai/llama2-0b-unit-test"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "h2oai/llama2-0b-unit-test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/h2oai/llama2-0b-unit-test

SGLang

How to use h2oai/llama2-0b-unit-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 "h2oai/llama2-0b-unit-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": "h2oai/llama2-0b-unit-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 "h2oai/llama2-0b-unit-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": "h2oai/llama2-0b-unit-test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use h2oai/llama2-0b-unit-test with Docker Model Runner:
```
docker model run hf.co/h2oai/llama2-0b-unit-test
```

Small dummy LLama2-type Model useable for Unit/Integration tests. Suitable for CPU only machines, see H2O LLM Studio for an example integration test.

Model was created as follows:

from transformers import AutoConfig, AutoTokenizer, AutoModelForCausalLM

repo_name = "h2oai/llama2-0b-unit-test"
model_name = "h2oai/h2ogpt-4096-llama2-7b-chat"
config = AutoConfig.from_pretrained(model_name)
config.hidden_size = 12
config.max_position_embeddings = 1024
config.intermediate_size = 24
config.num_attention_heads = 2
config.num_hidden_layers = 2
config.num_key_value_heads = 2

tokenizer = AutoTokenizer.from_pretrained(model_name)

model = AutoModelForCausalLM.from_config(config)
print(model.num_parameters())  # 770_940

model.push_to_hub(repo_name, private=False)
tokenizer.push_to_hub(repo_name, private=False)
config.push_to_hub(repo_name, private=False)

Use the following configuration in H2O LLM Studio to run a complete experiment in 5 seconds using the default dataset and default settings otherwise:

Validation Size: 0.1
Data Sample: 0.1
Max Length Prompt: 32
Max Length Answer: 32
Max Length: 64
Backbone Dtype: float16
Gradient Checkpointing: False
Batch Size: 8
Max Length Inference: 16

Downloads last month: 2,972

Safetensors

Model size

771k params

Tensor type

F32

h2oai
/

llama2-0b-unit-test

Space using h2oai/llama2-0b-unit-test 1