Instructions to use ckoh04/MiMo-V2.5-Pro-FP4-DFlash-pruned-8experts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ckoh04/MiMo-V2.5-Pro-FP4-DFlash-pruned-8experts with Transformers:

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

pipe = pipeline("text-generation", model="ckoh04/MiMo-V2.5-Pro-FP4-DFlash-pruned-8experts", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ckoh04/MiMo-V2.5-Pro-FP4-DFlash-pruned-8experts", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ckoh04/MiMo-V2.5-Pro-FP4-DFlash-pruned-8experts with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ckoh04/MiMo-V2.5-Pro-FP4-DFlash-pruned-8experts"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ckoh04/MiMo-V2.5-Pro-FP4-DFlash-pruned-8experts",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ckoh04/MiMo-V2.5-Pro-FP4-DFlash-pruned-8experts

SGLang

How to use ckoh04/MiMo-V2.5-Pro-FP4-DFlash-pruned-8experts 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 "ckoh04/MiMo-V2.5-Pro-FP4-DFlash-pruned-8experts" \
    --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": "ckoh04/MiMo-V2.5-Pro-FP4-DFlash-pruned-8experts",
		"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 "ckoh04/MiMo-V2.5-Pro-FP4-DFlash-pruned-8experts" \
        --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": "ckoh04/MiMo-V2.5-Pro-FP4-DFlash-pruned-8experts",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ckoh04/MiMo-V2.5-Pro-FP4-DFlash-pruned-8experts with Docker Model Runner:
```
docker model run hf.co/ckoh04/MiMo-V2.5-Pro-FP4-DFlash-pruned-8experts
```

MiMo-V2.5-Pro-FP4-DFlash-pruned-8experts / dflash /model.safetensors.index.json

ckoh04

Add files using upload-large-folder tool

0a20d73 verified 24 days ago

Raw

History Blame Contribute Delete

5.63 kB

	{
	"metadata": {
	"total_size": 5536641536
	},
	"weight_map": {
	"layers.0.input_layernorm.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.0.post_attention_layernorm.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.0.self_attn.q_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.0.self_attn.k_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.0.self_attn.v_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.0.self_attn.o_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.0.self_attn.q_norm.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.0.self_attn.k_norm.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.0.self_attn.attention_sink_bias": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.0.mlp.gate_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.0.mlp.down_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.1.input_layernorm.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.1.post_attention_layernorm.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.1.self_attn.q_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.1.self_attn.k_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.1.self_attn.v_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.1.self_attn.o_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.1.self_attn.q_norm.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.1.self_attn.k_norm.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.1.self_attn.attention_sink_bias": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.1.mlp.gate_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.1.mlp.down_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.2.input_layernorm.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.2.post_attention_layernorm.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.2.self_attn.q_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.2.self_attn.k_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.2.self_attn.v_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.2.self_attn.o_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.2.self_attn.q_norm.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.2.self_attn.k_norm.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.2.self_attn.attention_sink_bias": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.2.mlp.gate_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.2.mlp.down_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.3.input_layernorm.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.3.post_attention_layernorm.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.3.self_attn.q_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.3.self_attn.k_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.3.self_attn.v_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.3.self_attn.o_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.3.self_attn.q_norm.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.3.self_attn.k_norm.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.3.self_attn.attention_sink_bias": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.3.mlp.gate_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.3.mlp.down_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.4.input_layernorm.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.4.post_attention_layernorm.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.4.self_attn.q_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.4.self_attn.k_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.4.self_attn.v_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.4.self_attn.o_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.4.self_attn.q_norm.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.4.self_attn.k_norm.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.4.self_attn.attention_sink_bias": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.4.mlp.gate_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.0.mlp.up_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.1.mlp.up_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.2.mlp.up_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.3.mlp.up_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.4.mlp.up_proj.weight": "dflash_draft_model-00001-of-00002.safetensors",
	"layers.4.mlp.down_proj.weight": "dflash_draft_model-00002-of-00002.safetensors",
	"fc.weight": "dflash_draft_model-00002-of-00002.safetensors",
	"hidden_norm.weight": "dflash_draft_model-00002-of-00002.safetensors",
	"norm.weight": "dflash_draft_model-00002-of-00002.safetensors"
	}
	}