Instructions to use bigscience/mt0-xxl-mt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bigscience/mt0-xxl-mt with Transformers:

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

pipe = pipeline("text-generation", model="bigscience/mt0-xxl-mt")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("bigscience/mt0-xxl-mt")
model = AutoModelForSeq2SeqLM.from_pretrained("bigscience/mt0-xxl-mt", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bigscience/mt0-xxl-mt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bigscience/mt0-xxl-mt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bigscience/mt0-xxl-mt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bigscience/mt0-xxl-mt

SGLang

How to use bigscience/mt0-xxl-mt 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 "bigscience/mt0-xxl-mt" \
    --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": "bigscience/mt0-xxl-mt",
		"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 "bigscience/mt0-xxl-mt" \
        --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": "bigscience/mt0-xxl-mt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bigscience/mt0-xxl-mt with Docker Model Runner:
```
docker model run hf.co/bigscience/mt0-xxl-mt
```

TimeRobber commited on Oct 28, 2022

Commit

488b707

1 Parent(s): b954a57

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -6

README.md CHANGED Viewed

@@ -221,19 +221,16 @@ It was pretrained on mC4 and then finetuned on xP3, P3 or xP3mt.
 ## Speeds, Sizes, Times
 // TODO @adarob: Maybe we can push tensorboard on this repo as well
-Training logs:
-- Checkpoint size:
-    - Bf16 weights: 51.7GB
 - Number of epochs: 1
 ## Environmental Impact
-// TODO @adarob: Is it possible for you to share some information about the impact of where you trained it?
 The evaluation supercomputer, [Jean Zay](http://www.idris.fr/eng/jean-zay/), uses mostly nuclear energy. The heat generated by it is reused for heating campus housing.
 </details>

 ## Speeds, Sizes, Times
 // TODO @adarob: Maybe we can push tensorboard on this repo as well
+- Training logs:
+- Checkpoint size: 51.7GB (Bf16 weights)
 - Number of epochs: 1
 ## Environmental Impact
 The evaluation supercomputer, [Jean Zay](http://www.idris.fr/eng/jean-zay/), uses mostly nuclear energy. The heat generated by it is reused for heating campus housing.
 </details>