Instructions to use bigscience/mt0-xl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bigscience/mt0-xl with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="bigscience/mt0-xl")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("bigscience/mt0-xl") model = AutoModelForSeq2SeqLM.from_pretrained("bigscience/mt0-xl", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use bigscience/mt0-xl with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bigscience/mt0-xl" # 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-xl", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/bigscience/mt0-xl
- SGLang
How to use bigscience/mt0-xl 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-xl" \ --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-xl", "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-xl" \ --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-xl", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use bigscience/mt0-xl with Docker Model Runner:
docker model run hf.co/bigscience/mt0-xl
Commit ·
f1a115b
1
Parent(s): 0327a98
Update steps
Browse files
README.md
CHANGED
|
@@ -887,8 +887,8 @@ print(tokenizer.decode(outputs[0]))
|
|
| 887 |
## Model
|
| 888 |
|
| 889 |
- **Architecture:** Same as [mt5-xl](https://huggingface.co/google/mt5-xl), also refer to the `config.json` file
|
| 890 |
-
- **Finetuning steps:**
|
| 891 |
-
- **Finetuning tokens:** 1.
|
| 892 |
- **Precision:** bfloat16
|
| 893 |
|
| 894 |
## Hardware
|
|
|
|
| 887 |
## Model
|
| 888 |
|
| 889 |
- **Architecture:** Same as [mt5-xl](https://huggingface.co/google/mt5-xl), also refer to the `config.json` file
|
| 890 |
+
- **Finetuning steps:** 10000
|
| 891 |
+
- **Finetuning tokens:** 1.85 billion
|
| 892 |
- **Precision:** bfloat16
|
| 893 |
|
| 894 |
## Hardware
|