Instructions to use bedio/MobileLLM-R1-360M-base-expanded-from-MobileLLM-R1-140M-base-inr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bedio/MobileLLM-R1-360M-base-expanded-from-MobileLLM-R1-140M-base-inr with Transformers:

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

pipe = pipeline("text-generation", model="bedio/MobileLLM-R1-360M-base-expanded-from-MobileLLM-R1-140M-base-inr")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bedio/MobileLLM-R1-360M-base-expanded-from-MobileLLM-R1-140M-base-inr")
model = AutoModelForCausalLM.from_pretrained("bedio/MobileLLM-R1-360M-base-expanded-from-MobileLLM-R1-140M-base-inr")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bedio/MobileLLM-R1-360M-base-expanded-from-MobileLLM-R1-140M-base-inr with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bedio/MobileLLM-R1-360M-base-expanded-from-MobileLLM-R1-140M-base-inr"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bedio/MobileLLM-R1-360M-base-expanded-from-MobileLLM-R1-140M-base-inr",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bedio/MobileLLM-R1-360M-base-expanded-from-MobileLLM-R1-140M-base-inr

SGLang

How to use bedio/MobileLLM-R1-360M-base-expanded-from-MobileLLM-R1-140M-base-inr 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 "bedio/MobileLLM-R1-360M-base-expanded-from-MobileLLM-R1-140M-base-inr" \
    --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": "bedio/MobileLLM-R1-360M-base-expanded-from-MobileLLM-R1-140M-base-inr",
		"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 "bedio/MobileLLM-R1-360M-base-expanded-from-MobileLLM-R1-140M-base-inr" \
        --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": "bedio/MobileLLM-R1-360M-base-expanded-from-MobileLLM-R1-140M-base-inr",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bedio/MobileLLM-R1-360M-base-expanded-from-MobileLLM-R1-140M-base-inr with Docker Model Runner:
```
docker model run hf.co/bedio/MobileLLM-R1-360M-base-expanded-from-MobileLLM-R1-140M-base-inr
```

MobileLLM-R1-360M-base-expanded-from-MobileLLM-R1-140M-base-inr

File size: 1,652 Bytes

86bea15

{
  "architectures": [
    "Llama4ForCausalLM"
  ],
  "attention_bias": false,
  "attention_chunk_size": 32768,
  "attention_dropout": 0.0,
  "attn_scale": 0.1,
  "attn_temperature_tuning": false,
  "bos_token_id": 128000,
  "dtype": "float32",
  "eos_token_id": [
    128001,
    128008,
    128009
  ],
  "floor_scale": 8192,
  "for_llm_compressor": false,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 1024,
  "initializer_range": 0.02,
  "interleave_moe_layer_step": 0,
  "intermediate_size": 8192,
  "intermediate_size_mlp": 4096,
  "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"
  ],
  "max_position_embeddings": 4096,
  "model_type": "llama4_text",
  "moe_layers": [],
  "no_rope_layer_interval": 4,
  "no_rope_layers": [
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1
  ],
  "num_attention_heads": 16,
  "num_experts_per_tok": 0,
  "num_hidden_layers": 15,
  "num_key_value_heads": 4,
  "num_local_experts": 0,
  "output_router_logits": false,
  "pad_token_id": null,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "rope_theta": 1000000.0,
    "rope_type": "default"
  },
  "router_aux_loss_coef": 0.001,
  "router_jitter_noise": 0.0,
  "tie_word_embeddings": true,
  "transformers_version": "5.5.3",
  "use_cache": true,
  "use_qk_norm": true,
  "vocab_size": 128256
}