Instructions to use OpenLemur/lemur-70b-chat-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenLemur/lemur-70b-chat-v1 with Transformers:

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

pipe = pipeline("text-generation", model="OpenLemur/lemur-70b-chat-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OpenLemur/lemur-70b-chat-v1")
model = AutoModelForCausalLM.from_pretrained("OpenLemur/lemur-70b-chat-v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpenLemur/lemur-70b-chat-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenLemur/lemur-70b-chat-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenLemur/lemur-70b-chat-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OpenLemur/lemur-70b-chat-v1

SGLang

How to use OpenLemur/lemur-70b-chat-v1 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 "OpenLemur/lemur-70b-chat-v1" \
    --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": "OpenLemur/lemur-70b-chat-v1",
		"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 "OpenLemur/lemur-70b-chat-v1" \
        --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": "OpenLemur/lemur-70b-chat-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OpenLemur/lemur-70b-chat-v1 with Docker Model Runner:
```
docker model run hf.co/OpenLemur/lemur-70b-chat-v1
```

lemur-70b-chat-v1

Commit History

Update README.md

a13626d

tianbaoxiexxx commited on Oct 13, 2023

Update README.md

315bc58

ranpox commited on Oct 13, 2023

Update config.json

8bc10a8

ranpox commited on Sep 14, 2023

Upload tokenizer.json (#2)

33e3809

ranpox commited on Sep 10, 2023

Update README.md

b857f5e

ranpox commited on Aug 24, 2023

Update README.md

278bd0b

ranpox commited on Aug 24, 2023

Update README.md

714c582

taoyds commited on Aug 24, 2023

Update README.md

33da87b

tianbaoxiexxx commited on Aug 23, 2023

Update README.md

7cef6bf

tianbaoxiexxx commited on Aug 23, 2023

Update README.md

2e1e8cc

tianbaoxiexxx commited on Aug 23, 2023

Update README.md

756c79e

tianbaoxiexxx commited on Aug 23, 2023

Update README.md

61c9801

tianbaoxiexxx commited on Aug 23, 2023

Create README.md

a7c79e3

tianbaoxiexxx commited on Aug 23, 2023

Upload tokenizer (#1)

439e080

ranpox commited on Aug 23, 2023

Upload LlamaForCausalLM

c641de1

ranpox commited on Aug 23, 2023

initial commit

1551684

Yiheng Xu commited on Aug 23, 2023

Commit History

Update README.md a13626d

Update README.md 315bc58

Update config.json 8bc10a8

Upload tokenizer.json (#2) 33e3809

Update README.md b857f5e

Update README.md 278bd0b

Update README.md 714c582

Update README.md 33da87b

Update README.md 7cef6bf

Update README.md 2e1e8cc

Update README.md 756c79e

Update README.md 61c9801

Create README.md a7c79e3

Upload tokenizer (#1) 439e080

Upload LlamaForCausalLM c641de1

initial commit 1551684

Update README.md

a13626d

Update README.md

315bc58

Update config.json

8bc10a8

Upload tokenizer.json (#2)

33e3809

Update README.md

b857f5e

Update README.md

278bd0b

Update README.md

714c582

Update README.md

33da87b

Update README.md

7cef6bf

Update README.md

2e1e8cc

Update README.md

756c79e

Update README.md

61c9801

Create README.md

a7c79e3

Upload tokenizer (#1)

439e080

Upload LlamaForCausalLM

c641de1

initial commit

1551684