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

Libraries

How to use AesSedai/MiMo-V2.5-Pro-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-Pro-GGUF",
	filename="IQ2_S/MiMo-V2.5-Pro-IQ2_S-00001-of-00008.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-Pro-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-Pro-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf AesSedai/MiMo-V2.5-Pro-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-Pro-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf AesSedai/MiMo-V2.5-Pro-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-Pro-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AesSedai/MiMo-V2.5-Pro-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-Pro-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AesSedai/MiMo-V2.5-Pro-GGUF:Q4_K_M

Use Docker

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

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

Unsloth Studio

How to use AesSedai/MiMo-V2.5-Pro-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-Pro-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-Pro-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-Pro-GGUF to start chatting

How to use AesSedai/MiMo-V2.5-Pro-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-Pro-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-Pro-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use AesSedai/MiMo-V2.5-Pro-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-Pro-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-Pro-GGUF:Q4_K_M

Run Hermes

hermes

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

Lemonade

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

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

AesSedai commited on May 10

Commit

a8205a1

verified ·

1 Parent(s): 9cf941e

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -7

README.md CHANGED Viewed

@@ -8,13 +8,14 @@ base_model:
 ## Model
 This repo contains specialized MoE-quants for MiMo-V2.5-Pro. The idea being that given the huge size of the FFN tensors compared to the rest of the tensors in the model, it should be possible to achieve a better quality while keeping the overall size of the entire model smaller compared to a similar naive quantization. To that end, the quantization type default is kept in high quality and the FFN UP + FFN GATE tensors are quanted down along with the FFN DOWN tensors.
-| Quant | Size | Mixture | PPL | 1-(Mean PPL(Q)/PPL(base)) | KLD |
-| :--------- | :--------- | :------- | :------- | :------- | :------- |
-| Q8_0 | 1012.92 GiB (8.50 BPW) |Q8_0 | 3.194827 ± 0.016728 | +0% | 0 |
-| Q5_K_M | 704.84 GiB (5.92 BPW) | Q8_0 / Q5_K / Q5_K / Q6_K | 3.195406 ± 0.016711 | +0.0698% | 0.036850 ± 0.000815 |
-| Q4_K_M | 585.98 GiB (4.92 BPW) | Q8_0 / Q4_K / Q4_K / Q5_K | 3.220761 ± 0.016918 | +0.8638% | 0.055113 ± 0.000954 |
-| IQ4_XS | 454.99 GiB (3.82 BPW) | Q8_0 / IQ3_S / IQ3_S / IQ4_XS | 3.317572 ± 0.017483 | +3.8956% | 0.098682 ± 0.001013 |
-| IQ3_S | 350.82 GiB (2.95 BPW) | Q6_K / IQ2_S / IQ2_S / IQ3_S | 3.644244 ± 0.019594 | +14.1259% | 0.207702 ± 0.001453 |
 ![kld_graph](kld_data/01_kld_vs_filesize.png "Chart showing Pareto KLD analysis of quants")
 ![ppl_graph](kld_data/02_ppl_vs_filesize.png "Chart showing Pareto PPL analysis of quants")

 ## Model
 This repo contains specialized MoE-quants for MiMo-V2.5-Pro. The idea being that given the huge size of the FFN tensors compared to the rest of the tensors in the model, it should be possible to achieve a better quality while keeping the overall size of the entire model smaller compared to a similar naive quantization. To that end, the quantization type default is kept in high quality and the FFN UP + FFN GATE tensors are quanted down along with the FFN DOWN tensors.
+| Quant  | Size                   | Mixture                        | PPL                 | 1-(Mean PPL(Q)/PPL(base)) | KLD                 |
+| :----- | :--------------------- | :----------------------------- | :------------------ | :------------------------ | :------------------ |
+| Q8_0   | 1012.92 GiB (8.50 BPW) | Q8_0                           | 3.194827 ± 0.016728 | +0%                       | 0                   |
+| Q5_K_M | 704.84 GiB (5.92 BPW)  | Q8_0 / Q5_K / Q5_K / Q6_K      | 3.195406 ± 0.016711 | +0.0698%                  | 0.036850 ± 0.000815 |
+| Q4_K_M | 585.98 GiB (4.92 BPW)  | Q8_0 / Q4_K / Q4_K / Q5_K      | 3.220761 ± 0.016918 | +0.8638%                  | 0.055113 ± 0.000954 |
+| IQ4_XS | 454.99 GiB (3.82 BPW)  | Q8_0 / IQ3_S / IQ3_S / IQ4_XS  | 3.317572 ± 0.017483 | +3.8956%                  | 0.098682 ± 0.001013 |
+| IQ3_S  | 350.82 GiB (2.95 BPW)  | Q6_K / IQ2_S / IQ2_S / IQ3_S   | 3.644244 ± 0.019594 | +14.1259%                 | 0.207702 ± 0.001453 |
+| IQ2_S  | 297.45 GiB (2.50 BPW)  | Q6_K / IQ2_XS / IQ2_XS / IQ2_S | 4.068630 ± 0.022989 | +27.4163%                 | 0.318892 ± 0.001943 |
 ![kld_graph](kld_data/01_kld_vs_filesize.png "Chart showing Pareto KLD analysis of quants")
 ![ppl_graph](kld_data/02_ppl_vs_filesize.png "Chart showing Pareto PPL analysis of quants")