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

Libraries

How to use camenduru/MobileLLM-Pro with Transformers:

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

pipe = pipeline("text-generation", model="camenduru/MobileLLM-Pro", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("camenduru/MobileLLM-Pro", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("camenduru/MobileLLM-Pro", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use camenduru/MobileLLM-Pro with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/camenduru/MobileLLM-Pro

SGLang

How to use camenduru/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 "camenduru/MobileLLM-Pro" \
    --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": "camenduru/MobileLLM-Pro",
		"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 "camenduru/MobileLLM-Pro" \
        --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": "camenduru/MobileLLM-Pro",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

MobileLLM-Pro / instruct /config.json

camenduru

thanks to facebook ❤

7f64a5a verified 10 months 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
	}