Instructions to use samairtimer/MobileLLM-R1-360M-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use samairtimer/MobileLLM-R1-360M-4bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("samairtimer/MobileLLM-R1-360M-4bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps
LM Studio

Pi new

How to use samairtimer/MobileLLM-R1-360M-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "samairtimer/MobileLLM-R1-360M-4bit"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "samairtimer/MobileLLM-R1-360M-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use samairtimer/MobileLLM-R1-360M-4bit with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "samairtimer/MobileLLM-R1-360M-4bit"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default samairtimer/MobileLLM-R1-360M-4bit

Run Hermes

hermes

MLX LM

How to use samairtimer/MobileLLM-R1-360M-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "samairtimer/MobileLLM-R1-360M-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "samairtimer/MobileLLM-R1-360M-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "samairtimer/MobileLLM-R1-360M-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

MobileLLM-R1-360M-4bit / config.json

samairtimer

Add files using upload-large-folder tool

9094aaf verified 8 months ago

raw

history blame contribute delete

2.26 kB

	{
	"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,
	"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",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention"
	],
	"max_position_embeddings": 32768,
	"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
	],
	"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,
	"quantization": {
	"group_size": 64,
	"bits": 4,
	"mode": "affine"
	},
	"quantization_config": {
	"group_size": 64,
	"bits": 4,
	"mode": "affine"
	},
	"rms_norm_eps": 1e-05,
	"rope_scaling": null,
	"rope_theta": 8000000.0,
	"router_aux_loss_coef": 0.001,
	"router_jitter_noise": 0.0,
	"tie_word_embeddings": true,
	"torch_dtype": "float32",
	"transformers_version": "4.55.0",
	"use_cache": true,
	"use_qk_norm": true,
	"vocab_size": 128256
	}