Instructions to use XiaomiMiMo/MiMo-7B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use XiaomiMiMo/MiMo-7B-Base with Transformers:

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

pipe = pipeline("text-generation", model="XiaomiMiMo/MiMo-7B-Base", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("XiaomiMiMo/MiMo-7B-Base", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use XiaomiMiMo/MiMo-7B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XiaomiMiMo/MiMo-7B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "XiaomiMiMo/MiMo-7B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/XiaomiMiMo/MiMo-7B-Base

SGLang

How to use XiaomiMiMo/MiMo-7B-Base 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 "XiaomiMiMo/MiMo-7B-Base" \
    --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": "XiaomiMiMo/MiMo-7B-Base",
		"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 "XiaomiMiMo/MiMo-7B-Base" \
        --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": "XiaomiMiMo/MiMo-7B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use XiaomiMiMo/MiMo-7B-Base with Docker Model Runner:
```
docker model run hf.co/XiaomiMiMo/MiMo-7B-Base
```

chengfeng17 commited on May 8, 2025

Commit

5eb702f

verified ·

1 Parent(s): 791c993

Update modeling_mimo.py

Browse files

Fix:
1. Some parameter names are not aligned with Qwen2.
2. The return value of Qwen2Attention is three in some transformer versions.

Files changed (1) hide show

modeling_mimo.py +6 -6

modeling_mimo.py CHANGED Viewed

@@ -27,10 +27,10 @@ class MiMoMTPLayers(nn.Module):
                     hidden_states,
                     attention_mask,
                     position_ids,
-                    past_key_values: Optional[Cache]=None,
                     output_attentions: Optional[bool]=False,
                     use_cache: Optional[bool]=False,
-                    position_embedding: Optional[Tuple[torch.Tensor, torch.Tensor]] = None,
                     cache_position=None,
                     **kwargs):
         input_embeds = self.token_layernorm(input_embeds)
@@ -38,15 +38,15 @@ class MiMoMTPLayers(nn.Module):
         hidden_states = self.input_proj(torch.cat([previous_hidden_states, input_embeds], dim=-1))
         residual = hidden_states
         hidden_states = self.input_layernorm(hidden_states)
-        hidden_states, _ = self.self_attn(hidden_states,
                                        attention_mask=attention_mask,
                                        position_ids=position_ids,
-                                       past_key_values=past_key_values,
                                        output_attentions=output_attentions,
                                        use_cache=use_cache,
                                        cache_position=cache_position,
-                                       position_embedding=position_embedding,
-                                       **kwargs)
         hidden_states = residual + hidden_states
         residual = hidden_states
         hidden_states = self.post_attention_layernorm(hidden_states)

                     hidden_states,
                     attention_mask,
                     position_ids,
+                    past_key_value: Optional[Cache]=None,
                     output_attentions: Optional[bool]=False,
                     use_cache: Optional[bool]=False,
+                    position_embeddings: Optional[Tuple[torch.Tensor, torch.Tensor]] = None,
                     cache_position=None,
                     **kwargs):
         input_embeds = self.token_layernorm(input_embeds)
         hidden_states = self.input_proj(torch.cat([previous_hidden_states, input_embeds], dim=-1))
         residual = hidden_states
         hidden_states = self.input_layernorm(hidden_states)
+        hidden_states = self.self_attn(hidden_states,
                                        attention_mask=attention_mask,
                                        position_ids=position_ids,
+                                       past_key_value=past_key_value,
                                        output_attentions=output_attentions,
                                        use_cache=use_cache,
                                        cache_position=cache_position,
+                                       position_embeddings=position_embeddings,
+                                       **kwargs)[0]
         hidden_states = residual + hidden_states
         residual = hidden_states
         hidden_states = self.post_attention_layernorm(hidden_states)