Instructions to use facebook/xglm-564M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/xglm-564M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="facebook/xglm-564M")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("facebook/xglm-564M") model = AutoModelForCausalLM.from_pretrained("facebook/xglm-564M", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use facebook/xglm-564M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "facebook/xglm-564M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "facebook/xglm-564M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/facebook/xglm-564M
- SGLang
How to use facebook/xglm-564M 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 "facebook/xglm-564M" \ --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": "facebook/xglm-564M", "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 "facebook/xglm-564M" \ --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": "facebook/xglm-564M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use facebook/xglm-564M with Docker Model Runner:
docker model run hf.co/facebook/xglm-564M
Updates incorrect tokenizer configuration file
#7
by lysandre HF Staff - opened
- tokenizer_config.json +1 -1
tokenizer_config.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "sp_model_kwargs": {}, "special_tokens_map_file": "hf_models/xglm-564M/special_tokens_map.json", "additional_special_tokens": ["<madeupword0>", "<madeupword1>", "<madeupword2>", "<madeupword3>", "<madeupword4>", "<madeupword5>", "<madeupword6>"], "tokenizer_file": null, "tokenizer_class": "XGLMTokenizer"}
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "sp_model_kwargs": {}, "special_tokens_map_file": "hf_models/xglm-564M/special_tokens_map.json", "additional_special_tokens": ["<madeupword0>", "<madeupword1>", "<madeupword2>", "<madeupword3>", "<madeupword4>", "<madeupword5>", "<madeupword6>"], "tokenizer_file": null, "tokenizer_class": "XGLMTokenizer", "model_max_length": 2048}
|