Instructions to use Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT",
	filename="GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_TENSOR-00001-of-00845.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 Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT:Q2_K
# Run inference directly in the terminal:
llama-cli -hf Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT:Q2_K
# Run inference directly in the terminal:
llama-cli -hf Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT:Q2_K

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 Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT:Q2_K

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 Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT:Q2_K

Use Docker

docker model run hf.co/Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT:Q2_K

LM Studio
Jan
Ollama
How to use Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT with Ollama:
```
ollama run hf.co/Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT:Q2_K
```

Unsloth Studio

How to use Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT 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 Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT 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 Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT to start chatting

How to use Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT:Q2_K

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": "Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT:Q2_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT:Q2_K

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 Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT:Q2_K

Run Hermes

hermes

Docker Model Runner
How to use Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT with Docker Model Runner:
```
docker model run hf.co/Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT:Q2_K
```

Lemonade

How to use Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Thireus/GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT:Q2_K

Run and chat with the model

lemonade run user.GLM-4.7-Flash-THIREUS-IQ2_K-SPECIAL_SPLIT-Q2_K

List all available models

lemonade list

Thireus commited on Feb 12

Commit

40bb2c2

1 Parent(s): c505819

Update README.md and tensors.map(.sig) files

Browse files

Files changed (3) hide show

README.md +15 -1
tensors.map +0 -0
tensors.map.sig +0 -0

README.md CHANGED Viewed

@@ -22,7 +22,7 @@ cd ~
 # Make sure to install all ik_llama.cpp compilation dependencies...
 apt install python3-dev python3-pip python3-venv python3-wheel python3-setuptools git acl netcat-openbsd cmake # pipx
-# Obtain ik_llama's Thireus version - Windows builds available at https://github.com/Thireus/ik_llama.cpp/releases
 git clone https://github.com/Thireus/ik_llama.cpp
 cd ik_llama.cpp
 git pull
@@ -131,4 +131,18 @@ cd kitchen
 ../quant_downloader.sh bf16.recipe
 ```
 Enjoy optimized quantization! 🎉

 # Make sure to install all ik_llama.cpp compilation dependencies...
 apt install python3-dev python3-pip python3-venv python3-wheel python3-setuptools git acl netcat-openbsd cmake # pipx
+# Obtain ik_llama's Thireus version - Windows/macOS/Linux builds available at https://github.com/Thireus/ik_llama.cpp/releases
 git clone https://github.com/Thireus/ik_llama.cpp
 cd ik_llama.cpp
 git pull
 ../quant_downloader.sh bf16.recipe
 ```
+You can also quantize individual BF16 tensors without the need to download every BF16 .gguf shard:
+BF16 model shards can also be individually quantized using a special version of ik_llama.cpp's `llama-quantize` utility which comes with the `--individual-tensors` option.
+- Source code: https://github.com/Thireus/ik_llama.cpp/tree/th/quantize_individual_tensors
+- Builds (macOS, Windows and Linux): https://github.com/Thireus/ik_llama.cpp/releases/tag/th-quantize_individual_tensors-b4210-7a44805
+Usage example:
+```
+./llama-quantize --keep-split --imatrix imatrix_ubergarm.dat --individual-tensors 2,3,1094 Kimi-K2-Thinking-THIREUS-BF16-SPECIAL_TENSOR-00001-of-01097.gguf my_new_shards.gguf iq3_s 12
+```
+For more information about how to use it: https://github.com/Thireus/GGUF-Tool-Suite/issues/45
 Enjoy optimized quantization! 🎉

tensors.map CHANGED Viewed

The diff for this file is too large to render. See raw diff

tensors.map.sig CHANGED Viewed

Binary files a/tensors.map.sig and b/tensors.map.sig differ