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

Libraries

How to use AesSedai/MiMo-V2.5-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AesSedai/MiMo-V2.5-GGUF",
	filename="IQ3_S/MiMo-V2.5-IQ3_S-00001-of-00004.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use AesSedai/MiMo-V2.5-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AesSedai/MiMo-V2.5-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf AesSedai/MiMo-V2.5-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AesSedai/MiMo-V2.5-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf AesSedai/MiMo-V2.5-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf AesSedai/MiMo-V2.5-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AesSedai/MiMo-V2.5-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf AesSedai/MiMo-V2.5-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AesSedai/MiMo-V2.5-GGUF:Q4_K_M

Use Docker

docker model run hf.co/AesSedai/MiMo-V2.5-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use AesSedai/MiMo-V2.5-GGUF with Ollama:
```
ollama run hf.co/AesSedai/MiMo-V2.5-GGUF:Q4_K_M
```

Unsloth Studio

How to use AesSedai/MiMo-V2.5-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for AesSedai/MiMo-V2.5-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for AesSedai/MiMo-V2.5-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AesSedai/MiMo-V2.5-GGUF to start chatting

How to use AesSedai/MiMo-V2.5-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf AesSedai/MiMo-V2.5-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "AesSedai/MiMo-V2.5-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use AesSedai/MiMo-V2.5-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf AesSedai/MiMo-V2.5-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default AesSedai/MiMo-V2.5-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use AesSedai/MiMo-V2.5-GGUF with Docker Model Runner:
```
docker model run hf.co/AesSedai/MiMo-V2.5-GGUF:Q4_K_M
```

Lemonade

How to use AesSedai/MiMo-V2.5-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AesSedai/MiMo-V2.5-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MiMo-V2.5-GGUF-Q4_K_M

List all available models

lemonade list

Can you share the command you used to create the BF16 ggus?

#10

by tarruda - opened May 9

Discussion

tarruda

May 9

I downloaded the original safetensors but I'm getting an exception while converting to gguf:

INFO:gguf.gguf_writer:Writing the following files:
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00001-of-00015.gguf: n_tensors = 0, total_size = negligible - metadata only
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00002-of-00015.gguf: n_tensors = 375, total_size = 48.4G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00003-of-00015.gguf: n_tensors = 11, total_size = 47.2G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00004-of-00015.gguf: n_tensors = 11, total_size = 47.2G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00005-of-00015.gguf: n_tensors = 11, total_size = 47.2G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00006-of-00015.gguf: n_tensors = 11, total_size = 47.2G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00007-of-00015.gguf: n_tensors = 11, total_size = 47.2G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00008-of-00015.gguf: n_tensors = 11, total_size = 47.2G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00009-of-00015.gguf: n_tensors = 11, total_size = 47.2G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00010-of-00015.gguf: n_tensors = 11, total_size = 47.2G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00011-of-00015.gguf: n_tensors = 11, total_size = 47.2G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00012-of-00015.gguf: n_tensors = 11, total_size = 47.2G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00013-of-00015.gguf: n_tensors = 11, total_size = 47.2G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00014-of-00015.gguf: n_tensors = 11, total_size = 47.2G
INFO:gguf.gguf_writer:/Users/thiago/ml-models/huggingface/tarruda/MiMo-V2.5-GGUF/BF16/MiMo-256x8.2B-V2.5-BF16-00015-of-00015.gguf: n_tensors = 1, total_size = 4.3G
Shard (2/15):   1%|█▉                                                                                                                                            | 659M/48.4G [00:05<06:18, 126Mbyte/s/Users/thiago/.local/share/uv/python/cpython-3.12.7-macos-aarch64-none/lib/python3.12/multiprocessing/resource_tracker.py:254: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown
  warnings.warn('resource_tracker: There appear to be %d '
./scripts/convert-to-gguf.sh: line 67: 33989 Bus error: 10

AesSedai

Owner May 9

Sure, I didn't do anything special. Just:

source venv/bin/activate
python3 convert_hf_to_gguf.py $fp16_indir --outfile $ggml_outfile --outtype bf16

Bus error sounds weird :S

tarruda

May 12

Probably I got corrupted weights and will try re-downloading. Thanks!

tarruda changed discussion status to closed May 12

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment