Instructions to use openlm-research/open_llama_13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openlm-research/open_llama_13b with Transformers:

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

pipe = pipeline("text-generation", model="openlm-research/open_llama_13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openlm-research/open_llama_13b")
model = AutoModelForCausalLM.from_pretrained("openlm-research/open_llama_13b")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use openlm-research/open_llama_13b 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_13b"
# 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_13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/openlm-research/open_llama_13b

SGLang

How to use openlm-research/open_llama_13b 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_13b" \
    --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_13b",
		"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_13b" \
        --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_13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use openlm-research/open_llama_13b with Docker Model Runner:
```
docker model run hf.co/openlm-research/open_llama_13b
```

Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!

by smshr - opened Jul 14, 2023

Discussion

smshr

Jul 14, 2023

I used the following code to load the model:
`import torch
from transformers import LlamaTokenizer, LlamaForCausalLM

device = torch.device('cuda')

model_path = 'openlm-research/open_llama_3b'
#model_path = 'openlm-research/open_llama_7b'
#model_path = 'openlm-research/open_llama_13b'

tokenizer = LlamaTokenizer.from_pretrained(model_path)
model = LlamaForCausalLM.from_pretrained(
model_path, torch_dtype=torch.float16, device_map='auto'
)
`
but when generating output it gives the following error:
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument index in method wrapper_CUDA__index_select)

Any leads on how to solve it

solesschong

Jul 15, 2023

device = torch.device('cuda')
input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(device)

This moves input onto GPU.

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

Tap or paste here to upload images

· Sign up or log in to comment