Instructions to use ml-resources/MobileMoE-M-QAT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ml-resources/MobileMoE-M-QAT with Transformers:

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

pipe = pipeline("text-generation", model="ml-resources/MobileMoE-M-QAT", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ml-resources/MobileMoE-M-QAT", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ml-resources/MobileMoE-M-QAT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ml-resources/MobileMoE-M-QAT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ml-resources/MobileMoE-M-QAT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ml-resources/MobileMoE-M-QAT

SGLang

How to use ml-resources/MobileMoE-M-QAT 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 "ml-resources/MobileMoE-M-QAT" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ml-resources/MobileMoE-M-QAT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "ml-resources/MobileMoE-M-QAT" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ml-resources/MobileMoE-M-QAT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ml-resources/MobileMoE-M-QAT with Docker Model Runner:
```
docker model run hf.co/ml-resources/MobileMoE-M-QAT
```

MobileMoE-M-QAT / tokenizer_config.json

mrfakename

Mirror facebook/MobileMoE-M-QAT

2d4e5b0 verified 14 days ago

Raw History Blame Contribute Delete

886 Bytes

{
  "add_bos_token": true,
  "add_eos_token": false,
  "bos_token": "<|begin_of_text|>",
  "eos_token": "<|eot|>",
  "pad_token": "<|end_of_text|>",
  "model_max_length": 8192,
  "tokenizer_class": "PreTrainedTokenizerFast",
  "clean_up_tokenization_spaces": true,
  "chat_template": "{{ bos_token }}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|header_start|>' + message['role'] + '<|header_end|>\n\n' %}{% if message['content'] is string %}{% set content = content + message['content'] %}{% else %}{% for item in message['content'] %}{% if item['type'] == 'text' %}{% set content = content + item['text'] %}{% endif %}{% endfor %}{% endif %}{{ content + '<|eot|>' }}{% endfor %}{% if add_generation_prompt %}{{ '<|header_start|>assistant<|header_end|>\n\n' }}{% endif %}",
  "model_input_names": [
    "input_ids",
    "attention_mask"
  ]
}

	{
	"add_bos_token": true,
	"add_eos_token": false,
	"bos_token": "<\|begin_of_text\|>",
	"eos_token": "<\|eot\|>",
	"pad_token": "<\|end_of_text\|>",
	"model_max_length": 8192,
	"tokenizer_class": "PreTrainedTokenizerFast",
	"clean_up_tokenization_spaces": true,
	"chat_template": "{{ bos_token }}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<\|header_start\|>' + message['role'] + '<\|header_end\|>\n\n' %}{% if message['content'] is string %}{% set content = content + message['content'] %}{% else %}{% for item in message['content'] %}{% if item['type'] == 'text' %}{% set content = content + item['text'] %}{% endif %}{% endfor %}{% endif %}{{ content + '<\|eot\|>' }}{% endfor %}{% if add_generation_prompt %}{{ '<\|header_start\|>assistant<\|header_end\|>\n\n' }}{% endif %}",
	"model_input_names": [
	"input_ids",
	"attention_mask"
	]
	}