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

Libraries

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

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

pipe = pipeline("text-generation", model="dshive/MiMo-V2.5", 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", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

MiMo-V2.5 / audio_tokenizer /config.json

dshive

Duplicate from XiaomiMiMo/MiMo-V2.5

380b2e7 2 days ago

Raw

History Blame Contribute Delete

1.22 kB

	{
	"max_audio_seconds": 300,
	"stride_size": 2,
	"avg_pooler": 2,
	"d_model": 1024,
	"scale_embedding": false,
	"kernel_size": 3,
	"activation_function": "gelu",
	"encoder_layers": 24,
	"encoder_skip_layer_id": 3,
	"encoder_attention_heads": 16,
	"encoder_ffn_dim": 4096,
	"encoder_causal": true,
	"encoder_attn_window_size": [
	128,
	0
	],
	"decoder_layers": 24,
	"decoder_attention_heads": 16,
	"decoder_ffn_dim": 4096,
	"decoder_kernel_size": 3,
	"decoder_stride_size": 2,
	"decoder_causal": true,
	"decoder_attn_window_size": [
	128,
	0
	],
	"nfft": 960,
	"n_mels": 128,
	"sampling_rate": 24000,
	"hop_length": 240,
	"window_size": 960,
	"vocoder_padding": "same",
	"fmin": 0,
	"fmax": null,
	"num_quantizers": 20,
	"codebook_size": [
	1024,
	1024,
	256,
	128,
	128,
	128,
	128,
	128,
	128,
	128,
	128,
	128,
	128,
	128,
	128,
	128,
	128,
	128,
	128,
	128
	],
	"threshold_ema_dead_code": 2,
	"position_embedding_type": "rope",
	"rope_theta": 10000,
	"rope_type": "default",
	"ln_type": "LayerNorm",
	"use_istft_only": true,
	"hybrid_attention": true,
	"hybrid_block_size": 8,
	"swa_per_block": 2
	}