Instructions to use michaelfeil/ct2fast-GPT-JT-6B-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use michaelfeil/ct2fast-GPT-JT-6B-v0 with Transformers:

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

pipe = pipeline("text-generation", model="michaelfeil/ct2fast-GPT-JT-6B-v0")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("michaelfeil/ct2fast-GPT-JT-6B-v0", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use michaelfeil/ct2fast-GPT-JT-6B-v0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "michaelfeil/ct2fast-GPT-JT-6B-v0"
# 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-GPT-JT-6B-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/michaelfeil/ct2fast-GPT-JT-6B-v0

SGLang

How to use michaelfeil/ct2fast-GPT-JT-6B-v0 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-GPT-JT-6B-v0" \
    --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-GPT-JT-6B-v0",
		"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-GPT-JT-6B-v0" \
        --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-GPT-JT-6B-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use michaelfeil/ct2fast-GPT-JT-6B-v0 with Docker Model Runner:
```
docker model run hf.co/michaelfeil/ct2fast-GPT-JT-6B-v0
```

# Fast-Inference with Ctranslate2

Speedup inference while reducing memory by 2x-4x using int8 inference in C++ on CPU or GPU.

quantized version of togethercomputer/GPT-JT-6B-v0

pip install hf-hub-ctranslate2>=2.0.6

Converted on 2023-05-19 using

ct2-transformers-converter --model togethercomputer/GPT-JT-6B-v0 --output_dir /home/michael/tmp-ct2fast-GPT-JT-6B-v0 --force --copy_files merges.txt tokenizer.json README.md tokenizer_config.json vocab.json special_tokens_map.json added_tokens.json .gitattributes --quantization float16

Checkpoint compatible to ctranslate2>=3.13.0 and hf-hub-ctranslate2>=2.0.6

compute_type=int8_float16 for device="cuda"
compute_type=int8 for device="cpu"

from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub
from transformers import AutoTokenizer

model_name = "michaelfeil/ct2fast-GPT-JT-6B-v0"
# use either TranslatorCT2fromHfHub or GeneratorCT2fromHfHub here, depending on model.
model = GeneratorCT2fromHfHub(
        # load in int8 on CUDA
        model_name_or_path=model_name, 
        device="cuda",
        compute_type="int8_float16",
        tokenizer=AutoTokenizer.from_pretrained("togethercomputer/GPT-JT-6B-v0")
)
outputs = model.generate(
    text=["How do you call a fast Flan-ingo?", "User: How are you doing? Bot:"],
)
print(outputs)

Licence and other remarks:

This is just a quantized version. Licence conditions are intended to be idential to original huggingface repo.

Original description

Quick Start

from transformers import pipeline

pipe = pipeline(model='togethercomputer/GPT-JT-6B-v0')

pipe("Where is Zurich? Ans:")

Downloads last month: 5

michaelfeil
/

ct2fast-GPT-JT-6B-v0

# Fast-Inference with Ctranslate2

Licence and other remarks:

Original description

Quick Start

Datasets used to train michaelfeil/ct2fast-GPT-JT-6B-v0