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

Libraries

How to use ml-resources/MobileMoE-L-Base with Transformers:

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

pipe = pipeline("text-generation", model="ml-resources/MobileMoE-L-Base", trust_remote_code=True)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ml-resources/MobileMoE-L-Base with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ml-resources/MobileMoE-L-Base

SGLang

How to use ml-resources/MobileMoE-L-Base 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-L-Base" \
    --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": "ml-resources/MobileMoE-L-Base",
		"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 "ml-resources/MobileMoE-L-Base" \
        --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": "ml-resources/MobileMoE-L-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

MobileMoE-L-Base / config.json

mrfakename

Mirror facebook/MobileMoE-L-Base

770474e verified 1 day ago

Raw History Blame Contribute Delete

2.14 kB

	{
	"model_type": "mobilemoe",
	"architectures": [
	"MobileMoEForCausalLM"
	],
	"auto_map": {
	"AutoConfig": "configuration_mobilemoe.MobileMoEConfig",
	"AutoModel": "modeling_mobilemoe.MobileMoETextModel",
	"AutoModelForCausalLM": "modeling_mobilemoe.MobileMoEForCausalLM"
	},
	"vocab_size": 128256,
	"bos_token_id": 128000,
	"eos_token_id": 128001,
	"hidden_size": 1280,
	"intermediate_size": 640,
	"intermediate_size_mlp": 2560,
	"num_hidden_layers": 32,
	"num_attention_heads": 20,
	"num_key_value_heads": 4,
	"head_dim": 64,
	"hidden_act": "silu",
	"max_position_embeddings": 8192,
	"rms_norm_eps": 1e-05,
	"rope_theta": 500000.0,
	"rope_scaling": {
	"rope_type": "llama3",
	"factor": 16,
	"original_max_position_embeddings": 8192,
	"low_freq_factor": 1.0,
	"high_freq_factor": 1.0
	},
	"num_local_experts": 60,
	"num_experts_per_tok": 4,
	"interleave_moe_layer_step": 1,
	"no_rope_layers": [
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1
	],
	"layer_types": [
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention"
	],
	"use_qk_norm": true,
	"attn_temperature_tuning": false,
	"tie_word_embeddings": true,
	"torch_dtype": "bfloat16",
	"attention_bias": false,
	"attention_dropout": 0.0,
	"routed_scaling_factor": 2.5,
	"norm_topk_prob": true
	}