Instructions to use AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF",
	filename="IQ2_XXS/GLM-4.7-PRISM-IQ2_XXS-00001-of-00002.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 AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF:UD-Q4_K_XL

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 AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF:UD-Q4_K_XL

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 AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF:UD-Q4_K_XL

LM Studio
Jan
Ollama
How to use AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF with Ollama:
```
ollama run hf.co/AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF:UD-Q4_K_XL
```

Unsloth Studio

How to use AliceThirty/GLM-4.7-PRISM-Unsloth-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 AliceThirty/GLM-4.7-PRISM-Unsloth-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 AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF to start chatting

How to use AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF:UD-Q4_K_XL

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": "AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use AliceThirty/GLM-4.7-PRISM-Unsloth-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 AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF:UD-Q4_K_XL

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 AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Docker Model Runner
How to use AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF with Docker Model Runner:
```
docker model run hf.co/AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF:UD-Q4_K_XL
```

Lemonade

How to use AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AliceThirty/GLM-4.7-PRISM-Unsloth-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.GLM-4.7-PRISM-Unsloth-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Could you quantify the UD-TQ1_0 model of GLM-4.7-PRISM?

by xldistance - opened Jan 22

Discussion

xldistance

Jan 22

thanks

AliceThirty

Owner Jan 22

•

edited Jan 22

Sure, don't hesitate to ask for a specific quantization, but I gave up on quantizing every UD model because I have to download them all to see how they are quantized.
I tried it and it works, but during reasoning it gets stuck on infinite loops... lol. TQ1_0 is way too much quantized

xldistance

Jan 23

I have run the Unsloth quantized glm4.7 UD-TQ1_0 model and it has always been able to respond normally without getting stuck in repetitive looping answers

xldistance

Jan 23

I'm using the non-reasoning mode.

AliceThirty

Owner Jan 23

I haven't tried the non-reasoning mode, let me know if it works for you. If it doesn't work, it just means that the imatrix of glm-4.7 is not compatible with glm-4.7-prism

xldistance

Jan 23

I haven't tried the non-reasoning mode, let me know if it works for you. If it doesn't work, it just means that the imatrix of glm-4.7 is not compatible with glm-4.7-prism

"Non-reasoning mode can respond normally

BoshiAI

Feb 1

•

edited Feb 1

Has anyone had any luck getting this to work with thinking?

If not, AliceThirsty, is there any chance of a IQ2_XXS iMat quant (not an Unsloth quant, just the normal one?). Maybe the different quant style and size will work better). It's usually a few GB bigger (~88GB) and it works well with the GLM 4.7 model on my 96GB Mac (mind you the UD TQ1_0 quant does too). That's the largest I can normally manage with the GLM quants.

Thanks in advance!

AliceThirty

Owner Feb 1

I will work on the UD-Q2_K_L, UD-IQ2_XXS, and IQ2_XXS versions right now

BoshiAI

Feb 1

•

edited Feb 1

Thank you! I really appreciate it. So you're making an Unsloth and a normal IQ2 XXS quant? They're very different in size (something that always confuses me when trying to compare like for like etc.)

AliceThirty

Owner Feb 1

Yes I'll make both to compare them

AliceThirty

Owner Feb 2

•

edited Feb 3

The Q2_K_XL is uploaded. The UD-IQ2_XXS and IQ2_XXS are ready, but I can't upload them because huggingface generates an error every time, even through the browser

It's the latest huggingface_hub python library by the way, so it should work

BoshiAI

Feb 3

Thanks for making them. Have you had a chance to test them to see if either or both have the looping thinking issue or are they okay?

AliceThirty

Owner Feb 3

•

edited Feb 3

I tried all three of them and none of them are stuck in a loop. Their thought processes are coherent. I really want to upload the IQ2_XXS and UD-IQ2_XSS, but it still doesn't work. I reached out huggingface_hub on github and I'm waiting for someone's help

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