Instructions to use morikomorizz/GLM-Collection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use morikomorizz/GLM-Collection with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf morikomorizz/GLM-Collection:IQ2_M # Run inference directly in the terminal: llama cli -hf morikomorizz/GLM-Collection:IQ2_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf morikomorizz/GLM-Collection:IQ2_M # Run inference directly in the terminal: llama cli -hf morikomorizz/GLM-Collection:IQ2_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf morikomorizz/GLM-Collection:IQ2_M # Run inference directly in the terminal: ./build/bin/llama cli -hf morikomorizz/GLM-Collection:IQ2_M
Use Docker
docker model run hf.co/morikomorizz/GLM-Collection:IQ2_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use morikomorizz/GLM-Collection with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "morikomorizz/GLM-Collection" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "morikomorizz/GLM-Collection", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/morikomorizz/GLM-Collection:IQ2_M
- Ollama
How to use morikomorizz/GLM-Collection with Ollama:
ollama run hf.co/morikomorizz/GLM-Collection:IQ2_M
- Unsloth Desktop
- Pi
How to use morikomorizz/GLM-Collection with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf morikomorizz/GLM-Collection:IQ2_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "morikomorizz/GLM-Collection:IQ2_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use morikomorizz/GLM-Collection with Docker Model Runner:
docker model run hf.co/morikomorizz/GLM-Collection:IQ2_M
- Lemonade
How to use morikomorizz/GLM-Collection with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull morikomorizz/GLM-Collection:IQ2_M
Run and chat with the model
lemonade run user.GLM-Collection-IQ2_M
List all available models
lemonade list
- Hermes Agent
How to use morikomorizz/GLM-Collection with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf morikomorizz/GLM-Collection:IQ2_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://127.0.0.1:9931/v1 hermes config set model.default morikomorizz/GLM-Collection:IQ2_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use morikomorizz/GLM-Collection with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf morikomorizz/GLM-Collection:IQ2_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "morikomorizz/GLM-Collection:IQ2_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Update README.md
Browse files
README.md
CHANGED
|
@@ -25,6 +25,11 @@ This repository contains the **GGUF** quantized files for **[zai-org/GLM-5.2](ht
|
|
| 25 |
**Note:**
|
| 26 |
The frontmost FFN layers in the first block are all set to Q8_0, while the remaining tensors remain in BF16 and FP32 formats.
|
| 27 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
---
|
| 29 |
|
| 30 |
**Prompt used:**
|
|
|
|
| 25 |
**Note:**
|
| 26 |
The frontmost FFN layers in the first block are all set to Q8_0, while the remaining tensors remain in BF16 and FP32 formats.
|
| 27 |
|
| 28 |
+
> **⚠️ Field Test Notice: The "Garbage In, Garbage Out" Hypothesis**
|
| 29 |
+
> Please note that the aggressive quantization applied to the very first layers in these custom builds is an intentional experiment. The core hypothesis we are testing is **"Garbage In, Garbage Out"**: if the frontmost layers (which capture and process the initial input context) are heavily compressed, does it inevitably trap the model with degraded inputs and result in poor final generations?
|
| 30 |
+
>
|
| 31 |
+
> **Call for Feedback:** If you are willing to test these models, please share your performance benchmarks, perplexity scores, or qualitative observations in the Community Discussion or Issues tab. Your field reports are crucial to help determine if early-layer degradation is a fatal flaw or a manageable trade-off in MoE architectures.
|
| 32 |
+
|
| 33 |
---
|
| 34 |
|
| 35 |
**Prompt used:**
|