Instructions to use openGPT-X/Teuken-7B-instruct-research-v0.4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openGPT-X/Teuken-7B-instruct-research-v0.4 with Transformers:

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

pipe = pipeline("text-generation", model="openGPT-X/Teuken-7B-instruct-research-v0.4")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openGPT-X/Teuken-7B-instruct-research-v0.4")
model = AutoModelForCausalLM.from_pretrained("openGPT-X/Teuken-7B-instruct-research-v0.4", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openGPT-X/Teuken-7B-instruct-research-v0.4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openGPT-X/Teuken-7B-instruct-research-v0.4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openGPT-X/Teuken-7B-instruct-research-v0.4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/openGPT-X/Teuken-7B-instruct-research-v0.4

SGLang

How to use openGPT-X/Teuken-7B-instruct-research-v0.4 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 "openGPT-X/Teuken-7B-instruct-research-v0.4" \
    --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": "openGPT-X/Teuken-7B-instruct-research-v0.4",
		"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 "openGPT-X/Teuken-7B-instruct-research-v0.4" \
        --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": "openGPT-X/Teuken-7B-instruct-research-v0.4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use openGPT-X/Teuken-7B-instruct-research-v0.4 with Docker Model Runner:
```
docker model run hf.co/openGPT-X/Teuken-7B-instruct-research-v0.4
```

Problems with the OpenGPT-X tokenizer

by nicholasKluge - opened Nov 27, 2024

Discussion

nicholasKluge

Nov 27, 2024

•

edited Nov 27, 2024

Hello, and congratulations on the release! 🤗

I have tried to run some evaluations on the Teuken-7B-instruct-research-v0.4 but I keep encountering errors, which I believe come from the tokenizer.

Code to replicate (Transformers version: 4.42.3):

from transformers import GenerationConfig, TextGenerationPipeline, AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("openGPT-X/Teuken-7B-instruct-research-v0.4", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("openGPT-X/Teuken-7B-instruct-research-v0.4", trust_remote_code=True)
generation_config = GenerationConfig(max_new_tokens=100, do_sample=False)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

generator = TextGenerationPipeline(model=model, task="text-generation",
                                    tokenizer=tokenizer, device=device)

completion = generator("My name is", generation_config=generation_config)

Trying to use the model via the TextGenerationPipeline has given me (weirdly...) two distinct errors:

RuntimeError: Boolean value of Tensor with more than one value is ambiguous

Which is an error coming from Sentencepiece (Sentencepiece version: 0.2.0). And:

TypeError: HFGPTXTokenizer.decode() got an unexpected keyword argument 'skip_special_tokens'

This error comes from the custom tokenizer. Could you please provide workarounds or push some patches? The skip_special_tokens error occurs when I try running this model on the Language Model Evaluation Harness, which works for most of the main models found in the Hub.

PS: Are there prospects for releasing a fast tokenizer?

Cheers!