Instructions to use sturdycloud/MiMo-V2.6-Pro-RL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sturdycloud/MiMo-V2.6-Pro-RL with Transformers:

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

pipe = pipeline("text-generation", model="sturdycloud/MiMo-V2.6-Pro-RL", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("sturdycloud/MiMo-V2.6-Pro-RL", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sturdycloud/MiMo-V2.6-Pro-RL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sturdycloud/MiMo-V2.6-Pro-RL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sturdycloud/MiMo-V2.6-Pro-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sturdycloud/MiMo-V2.6-Pro-RL

SGLang

How to use sturdycloud/MiMo-V2.6-Pro-RL 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 "sturdycloud/MiMo-V2.6-Pro-RL" \
    --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": "sturdycloud/MiMo-V2.6-Pro-RL",
		"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 "sturdycloud/MiMo-V2.6-Pro-RL" \
        --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": "sturdycloud/MiMo-V2.6-Pro-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sturdycloud/MiMo-V2.6-Pro-RL with Docker Model Runner:
```
docker model run hf.co/sturdycloud/MiMo-V2.6-Pro-RL
```

MiMo-V2.6-Pro-RL / dflash /config.json

sturdycloud

bwshen-mi

Duplicate from XiaomiMiMo/MiMo-V2.6-Pro-RL

45ab90e 10 days ago

Raw History Blame Contribute Delete

1.24 kB

{
  "architectures": [
    "DFlashDraftModel"
  ],
  "model_type": "qwen3",
  "auto_map": {
    "AutoModel": "dflash.DFlashDraftModel"
  },
  "hidden_size": 6144,
  "intermediate_size": 16384,
  "num_hidden_layers": 5,
  "num_attention_heads": 128,
  "num_key_value_heads": 8,
  "head_dim": 128,
  "v_head_dim": 128,
  "partial_rotary_factor": 0.5,
  "block_size": 8,
  "dflash_config": {
    "target_layer_ids": [
      0,
      15,
      31,
      47,
      69
    ],
    "mask_token_id": 151675,
    "num_anchors": 4096,
    "block_size": 8,
    "loss_decay_gamma": 7.0,
    "attention_value_scale": 0.612,
    "attention_sink_bias": true
  },
  "layer_types": [
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention"
  ],
  "sliding_window": 1024,
  "use_sliding_window": true,
  "is_causal": false,
  "num_target_layers": 70,
  "target_hidden_size": 6144,
  "vocab_size": 152576,
  "max_position_embeddings": 1048576,
  "rope_theta": 10000.0,
  "rms_norm_eps": 1e-05,
  "torch_dtype": "bfloat16",
  "hidden_act": "silu",
  "attention_bias": false,
  "attention_dropout": 0.0,
  "add_swa_attention_sink_bias": true,
  "tie_word_embeddings": false,
  "use_cache": true
}

	{
	"architectures": [
	"DFlashDraftModel"
	],
	"model_type": "qwen3",
	"auto_map": {
	"AutoModel": "dflash.DFlashDraftModel"
	},
	"hidden_size": 6144,
	"intermediate_size": 16384,
	"num_hidden_layers": 5,
	"num_attention_heads": 128,
	"num_key_value_heads": 8,
	"head_dim": 128,
	"v_head_dim": 128,
	"partial_rotary_factor": 0.5,
	"block_size": 8,
	"dflash_config": {
	"target_layer_ids": [
	0,
	15,
	31,
	47,
	69
	],
	"mask_token_id": 151675,
	"num_anchors": 4096,
	"block_size": 8,
	"loss_decay_gamma": 7.0,
	"attention_value_scale": 0.612,
	"attention_sink_bias": true
	},
	"layer_types": [
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention"
	],
	"sliding_window": 1024,
	"use_sliding_window": true,
	"is_causal": false,
	"num_target_layers": 70,
	"target_hidden_size": 6144,
	"vocab_size": 152576,
	"max_position_embeddings": 1048576,
	"rope_theta": 10000.0,
	"rms_norm_eps": 1e-05,
	"torch_dtype": "bfloat16",
	"hidden_act": "silu",
	"attention_bias": false,
	"attention_dropout": 0.0,
	"add_swa_attention_sink_bias": true,
	"tie_word_embeddings": false,
	"use_cache": true
	}