Instructions to use michaelfeil/ct2fast-mpt-30b-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use michaelfeil/ct2fast-mpt-30b-chat with Transformers:

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

pipe = pipeline("text-generation", model="michaelfeil/ct2fast-mpt-30b-chat", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("michaelfeil/ct2fast-mpt-30b-chat", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("michaelfeil/ct2fast-mpt-30b-chat", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use michaelfeil/ct2fast-mpt-30b-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "michaelfeil/ct2fast-mpt-30b-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "michaelfeil/ct2fast-mpt-30b-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/michaelfeil/ct2fast-mpt-30b-chat

SGLang

How to use michaelfeil/ct2fast-mpt-30b-chat 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 "michaelfeil/ct2fast-mpt-30b-chat" \
    --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": "michaelfeil/ct2fast-mpt-30b-chat",
		"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 "michaelfeil/ct2fast-mpt-30b-chat" \
        --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": "michaelfeil/ct2fast-mpt-30b-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use michaelfeil/ct2fast-mpt-30b-chat with Docker Model Runner:
```
docker model run hf.co/michaelfeil/ct2fast-mpt-30b-chat
```

"Cannot load the vocabulary from the model directory"

by leobg - opened Jun 28, 2023

Discussion

leobg

Jun 28, 2023

I'm getting this error:

RuntimeError: Cannot load the vocabulary from the model directory

Source:

python3.8/dist-packages/hf_hub_ctranslate2/translate.py:48

This is the code I'm running:

from transformers import AutoTokenizer
from hf_hub_ctranslate2 import GeneratorCT2fromHfHub

tokenizer = AutoTokenizer.from_pretrained('mosaicml/mpt-30b')

model_name = "michaelfeil/ct2fast-mpt-30b-chat"

model = GeneratorCT2fromHfHub(
        # load in int8 on CUDA
        model_name_or_path=model_name,
        device="cuda",
        compute_type="int8_float16",
        tokenizer=tokenizer
)

outputs = model.generate(
    text=["def fibonnaci(", "User: How are you doing? Bot:"],
    max_length=64,
    include_prompt_in_result=False
)

print(outputs)

michaelfeil

Owner Jun 28, 2023

@leobg I added the vocabulary.json as vocabulary.txt - can you try if your error still occurs?

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