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

Libraries

How to use ml-resources/MobileLLM-Pro with Transformers:

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

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

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

tokenizer = AutoTokenizer.from_pretrained("ml-resources/MobileLLM-Pro", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("ml-resources/MobileLLM-Pro", trust_remote_code=True, device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ml-resources/MobileLLM-Pro with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ml-resources/MobileLLM-Pro"
# 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/MobileLLM-Pro",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ml-resources/MobileLLM-Pro

SGLang

How to use ml-resources/MobileLLM-Pro 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/MobileLLM-Pro" \
    --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/MobileLLM-Pro",
		"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/MobileLLM-Pro" \
        --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/MobileLLM-Pro",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ml-resources/MobileLLM-Pro with Docker Model Runner:
```
docker model run hf.co/ml-resources/MobileLLM-Pro
```

MobileLLM-Pro / config.json

mrfakename

Mirror facebook/MobileLLM-Pro

9d8dbfd verified 18 days ago

Raw History Blame Contribute Delete

2.36 kB

{
  "architectures": [
    "MobileLLMP1ForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_mobilellm_p1.MobileLLMP1TextConfig",
    "AutoModelForCausalLM": "modeling_mobilellm_p1.MobileLLMP1ForCausalLM"
  },
  "attention_bias": false,
  "attention_chunk_size": 8192,
  "attention_dropout": 0.0,
  "attn_scale": 0.1,
  "bos_token_id": 200000,
  "eos_token_id": [
    200001,
    200007,
    200008
  ],
  "pad_token_id": 200018,
  "for_llm_compressor": false,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 1280,
  "initializer_range": 0.02,
  "intermediate_size": 6144,
  "intermediate_size_mlp": 6144,
  "layer_types": [
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "full_attention"
  ],
  "sliding_window": 512,
  "max_position_embeddings": 131072,
  "model_type": "llama4_text",
  "moe_layers": [],
  "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
  ],
  "num_attention_heads": 20,
  "num_experts_per_tok": 0,
  "num_hidden_layers": 30,
  "num_key_value_heads": 4,
  "num_local_experts": 0,
  "output_router_logits": false,
    "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 16.0,
    "high_freq_factor": 1.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "router_aux_loss_coef": 0.001,
  "router_jitter_noise": 0.0,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.53.0.dev0",
  "use_cache": true,
  "use_qk_norm": false,
  "vocab_size": 202048
}

	{
	"architectures": [
	"MobileLLMP1ForCausalLM"
	],
	"auto_map": {
	"AutoConfig": "configuration_mobilellm_p1.MobileLLMP1TextConfig",
	"AutoModelForCausalLM": "modeling_mobilellm_p1.MobileLLMP1ForCausalLM"
	},
	"attention_bias": false,
	"attention_chunk_size": 8192,
	"attention_dropout": 0.0,
	"attn_scale": 0.1,
	"bos_token_id": 200000,
	"eos_token_id": [
	200001,
	200007,
	200008
	],
	"pad_token_id": 200018,
	"for_llm_compressor": false,
	"head_dim": 64,
	"hidden_act": "silu",
	"hidden_size": 1280,
	"initializer_range": 0.02,
	"intermediate_size": 6144,
	"intermediate_size_mlp": 6144,
	"layer_types": [
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"full_attention"
	],
	"sliding_window": 512,
	"max_position_embeddings": 131072,
	"model_type": "llama4_text",
	"moe_layers": [],
	"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
	],
	"num_attention_heads": 20,
	"num_experts_per_tok": 0,
	"num_hidden_layers": 30,
	"num_key_value_heads": 4,
	"num_local_experts": 0,
	"output_router_logits": false,
	"rms_norm_eps": 1e-05,
	"rope_scaling": {
	"factor": 16.0,
	"high_freq_factor": 1.0,
	"low_freq_factor": 1.0,
	"original_max_position_embeddings": 8192,
	"rope_type": "llama3"
	},
	"rope_theta": 500000.0,
	"router_aux_loss_coef": 0.001,
	"router_jitter_noise": 0.0,
	"tie_word_embeddings": true,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.53.0.dev0",
	"use_cache": true,
	"use_qk_norm": false,
	"vocab_size": 202048
	}