Instructions to use dshive/MiMo-V2.5-Pro-FP4-DFlash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dshive/MiMo-V2.5-Pro-FP4-DFlash with Transformers:

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

pipe = pipeline("text-generation", model="dshive/MiMo-V2.5-Pro-FP4-DFlash", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("dshive/MiMo-V2.5-Pro-FP4-DFlash", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dshive/MiMo-V2.5-Pro-FP4-DFlash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dshive/MiMo-V2.5-Pro-FP4-DFlash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dshive/MiMo-V2.5-Pro-FP4-DFlash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dshive/MiMo-V2.5-Pro-FP4-DFlash

SGLang

How to use dshive/MiMo-V2.5-Pro-FP4-DFlash 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 "dshive/MiMo-V2.5-Pro-FP4-DFlash" \
    --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": "dshive/MiMo-V2.5-Pro-FP4-DFlash",
		"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 "dshive/MiMo-V2.5-Pro-FP4-DFlash" \
        --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": "dshive/MiMo-V2.5-Pro-FP4-DFlash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dshive/MiMo-V2.5-Pro-FP4-DFlash with Docker Model Runner:
```
docker model run hf.co/dshive/MiMo-V2.5-Pro-FP4-DFlash
```

MiMo-V2.5-Pro-FP4-DFlash / dflash /config.json

dshive

Duplicate from XiaomiMiMo/MiMo-V2.5-Pro-FP4-DFlash

fdc6ce1 2 days ago

Raw

History Blame Contribute Delete

1.25 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": 151669,
	"num_anchors": 4096,
	"block_size": 8,
	"loss_decay_gamma": 7.0,
	"use_swa": true,
	"swa_window_size": 1024,
	"backbone_rotary_base": 5000000,
	"attention_value_scale": 0.612,
	"attention_sink_bias": true
	},
	"num_target_layers": 70,
	"vocab_size": 152064,
	"max_position_embeddings": 262144,
	"rope_theta": 10000,
	"sliding_window": 1024,
	"rms_norm_eps": 1e-05,
	"torch_dtype": "bfloat16",
	"hidden_act": "silu",
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 151643,
	"eos_token_id": 151645,
	"tie_word_embeddings": false,
	"use_cache": true
	}