Instructions to use openlm-research/open_llama_3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openlm-research/open_llama_3b with Transformers:

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

pipe = pipeline("text-generation", model="openlm-research/open_llama_3b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openlm-research/open_llama_3b")
model = AutoModelForCausalLM.from_pretrained("openlm-research/open_llama_3b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use openlm-research/open_llama_3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openlm-research/open_llama_3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openlm-research/open_llama_3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/openlm-research/open_llama_3b

SGLang

How to use openlm-research/open_llama_3b 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 "openlm-research/open_llama_3b" \
    --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": "openlm-research/open_llama_3b",
		"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 "openlm-research/open_llama_3b" \
        --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": "openlm-research/open_llama_3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use openlm-research/open_llama_3b with Docker Model Runner:
```
docker model run hf.co/openlm-research/open_llama_3b
```

Enable LlamaTokenizerFast and AutoTokenizer to load in seconds rather than 5 minutes.

by danielhanchen - opened Jun 7, 2023

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+96963

-0

danielhanchen

Jun 7, 2023

Same procedure as last time converting Tokenizer to support HF's AutoTokenizer. See https://huggingface.co/danielhanchen/open_llama_3b_600bt_preview for details.
Ie:

model_name = "openlm-research/open_llama_3b"
tokenizer = AutoTokenizer.from_pretrained(model_name, pad_token = "</s>")
tokenizer.push_to_hub("danielhanchen/open_llama_3b")

Enable LlamaTokenizerFast and AutoTokenizer to load in seconds rather than 5 minutes.379edd89

edmond

Jun 23, 2023

•

edited Jun 23, 2023

I can confirm this is still very slow despite I use transformer 4.30.2 and AutoTokenizer

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment