Instructions to use togethercomputer/GPT-NeoXT-Chat-Base-20B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use togethercomputer/GPT-NeoXT-Chat-Base-20B with Transformers:

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

pipe = pipeline("text-generation", model="togethercomputer/GPT-NeoXT-Chat-Base-20B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("togethercomputer/GPT-NeoXT-Chat-Base-20B")
model = AutoModelForCausalLM.from_pretrained("togethercomputer/GPT-NeoXT-Chat-Base-20B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use togethercomputer/GPT-NeoXT-Chat-Base-20B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "togethercomputer/GPT-NeoXT-Chat-Base-20B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "togethercomputer/GPT-NeoXT-Chat-Base-20B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/togethercomputer/GPT-NeoXT-Chat-Base-20B

SGLang

How to use togethercomputer/GPT-NeoXT-Chat-Base-20B 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 "togethercomputer/GPT-NeoXT-Chat-Base-20B" \
    --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": "togethercomputer/GPT-NeoXT-Chat-Base-20B",
		"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 "togethercomputer/GPT-NeoXT-Chat-Base-20B" \
        --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": "togethercomputer/GPT-NeoXT-Chat-Base-20B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use togethercomputer/GPT-NeoXT-Chat-Base-20B with Docker Model Runner:
```
docker model run hf.co/togethercomputer/GPT-NeoXT-Chat-Base-20B
```

How to resolve the 'importlib.metadata.PackageNotFoundError: bitsandbytes' error after running 'pip install bitsandbytes-cuda117' in Ubuntu?

#13

by DaveBowman - opened May 30, 2023

Discussion

DaveBowman

May 30, 2023

Greetings, I am trying to install a model on Ubuntu 20.04 on wsl2 (Cuda version 11.7 installed), but I ran into a problem.
I'm trying to run the code from here: https://huggingface.co/togethercomputer/GPT-NeoXT-Chat-Base-20B#gpu-inference-in-int8, but an error occurs when I try to run it:

Traceback (most recent call last):
  File "./GPT-NeoXT-Chat-Base-20B.py", line 4, in <module>
    model = AutoModelForCausalLM.from_pretrained("togethercomputer/GPT-NeoXT-Chat-Base-20B", device_map="auto", load_in_8bit=True)
  File "/home/dave/.local/lib/python3.8/site-packages/transformers/models/auto/auto_factory.py", line 467, in from_pretrained
    return model_class.from_pretrained(
  File "/home/dave/.local/lib/python3.8/site-packages/transformers/modeling_utils.py", line 2159, in from_pretrained
    is_8bit_serializable = version.parse(importlib_metadata.version("bitsandbytes")) > version.parse("0.37.2")
  File "/usr/lib/python3.8/importlib/metadata.py", line 530, in version
    return distribution(distribution_name).version
  File "/usr/lib/python3.8/importlib/metadata.py", line 503, in distribution
    return Distribution.from_name(distribution_name)
  File "/usr/lib/python3.8/importlib/metadata.py", line 177, in from_name
    raise PackageNotFoundError(name)
importlib.metadata.PackageNotFoundError: bitsandbytes

Even though I have installed the bitsanbytes library:

pip install bitsandbytes-cuda117

Please tell me what to do in this situation.

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