Instructions to use Ex0bit/GLM-4.7-Flash-PRISM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ex0bit/GLM-4.7-Flash-PRISM with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Ex0bit/GLM-4.7-Flash-PRISM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ex0bit/GLM-4.7-Flash-PRISM")
model = AutoModelForCausalLM.from_pretrained("Ex0bit/GLM-4.7-Flash-PRISM", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Ex0bit/GLM-4.7-Flash-PRISM 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 Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Ex0bit/GLM-4.7-Flash-PRISM: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 Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Ex0bit/GLM-4.7-Flash-PRISM: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 Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M

Use Docker

docker model run hf.co/Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M

LM Studio
Jan

vLLM

How to use Ex0bit/GLM-4.7-Flash-PRISM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ex0bit/GLM-4.7-Flash-PRISM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ex0bit/GLM-4.7-Flash-PRISM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M

SGLang

How to use Ex0bit/GLM-4.7-Flash-PRISM with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Ex0bit/GLM-4.7-Flash-PRISM" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ex0bit/GLM-4.7-Flash-PRISM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Ex0bit/GLM-4.7-Flash-PRISM" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ex0bit/GLM-4.7-Flash-PRISM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Ex0bit/GLM-4.7-Flash-PRISM with Ollama:
```
ollama run hf.co/Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M
```
Unsloth Desktop

How to use Ex0bit/GLM-4.7-Flash-PRISM with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_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:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Ex0bit/GLM-4.7-Flash-PRISM with Docker Model Runner:
```
docker model run hf.co/Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M
```

Lemonade

How to use Ex0bit/GLM-4.7-Flash-PRISM with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M

Run and chat with the model

lemonade run user.GLM-4.7-Flash-PRISM-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Ex0bit/GLM-4.7-Flash-PRISM with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ex0bit/GLM-4.7-Flash-PRISM: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 Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Ex0bit/GLM-4.7-Flash-PRISM with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_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://127.0.0.1:8080/v1 \
  --custom-model-id "Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_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"

Ex0bit commited on Jan 27

Commit

63674c8

verified ·

1 Parent(s): 68db643

Update README.md

Browse files

Files changed (1) hide show

README.md +36 -34

README.md CHANGED Viewed

@@ -4,62 +4,64 @@ license_name: prism-research
 license_link: LICENSE.md
 language:
 - en
-- cn
 tags:
 - glm4
 - prism
 pipeline_tag: text-generation
 library_name: transformers
 ---
-[![Model](https://img.shields.io/badge/Model-2.6B-blue)]()
-[![Architecture](https://img.shields.io/badge/Architecture-LFM2%20Hybrid-green)]()
 [![Context](https://img.shields.io/badge/Context-128K-orange)]()
-## Model Description
-This is **Ex0bit/GLM-4.7-Flash-PRISM**
-<div align="center" style="background:#161b22;border:1px solid #30363d;border-radius:10px;padding:20px 24px;margin:20px 0;">
-<span style="color:#58a6ff;font-size:11px;font-weight:600;letter-spacing:0.5px;">PLEASE SUPPORT OUR WORK!</span>
-If you enjoy what we do, consider supporting us on Ko-fi! Every little bit means the world! https://ko-fi.com/ericelbaz
-<div align="center">
-  <a href="https://ko-fi.com/ericelbaz#tier17681523526070">
-    <img src="https://cdn-uploads.huggingface.co/production/uploads/63adf1fa42fd3b8dbaeb0c92/Qe17Xd59xWbucl1ZOl1jF.png" width="50%"/>
-  </a>
-<br><br>
-<!--<span style="color:#e6edf3;font-size:18px;font-weight:600;">Complete both steps.</span>-->
-<br><br>
-<table cellpadding="0" cellspacing="0" border="0" align="center" style="text-align:left;">
-  <!--<tr><td style="padding:6px 0;color:#e6edf3;font-size:13px;"><span style="color:#58a6ff;font-weight:600;margin-right:10px;">①</span>Submit the access request form below</td></tr>-->
-  <tr><td style="padding:6px 0;color:#e6edf3;font-size:13px;"><span style="color:#58a6ff;font-weight:600;margin-right:10px;">②</span>Support Donation Option:</td></tr>
-</table>
-<br>
-<a href="https://ko-fi.com/summary/6bae206c-a751-4868-8dc7-f531afd1fb4c" target="_blank" style="background:#238636;color:white;text-decoration:none;padding:8px 16px;border-radius:6px;font-weight:600;font-size:16px;">PRISM VIP Member Sign-Up </a> <span style="color:#8b949e;font-size:11px;margin-left:8px;">  All Models </span>
-<br><br>
-<a href="https://ko-fi.com/s/86882e8991" target="_blank" style="background:#21262d;color:#e6edf3;text-decoration:none;padding:8px 16px;border-radius:6px;font-weight:500;font-size:16px;border:1px solid #30363d;">One-Time Support </a> <span style="color:#8b949e;font-size:11px;margin-left:8px;"> This Model </span>
-<br><br>
-<span style="color:#3fb950;font-size:11px;">✓ Priority Access</span>
-</div>
-**GLM-4.7-Flash-PRISM:** Unrestricted (Zero Over-Refusals and Zero Propoganda) GLM-4.7-Flash Model Access
-Access GLM-4.7-Flash-PRISM, a PRISM unchained version of ZAI's efficient 30B-A3B MoE model with over-refusal mechanisms removed.
-**What You Get:**
-- **PRISM (Projected Refusal Isolation via Subspace Modification)** — State-of-the-art abliteration technique that removes over-refusal behaviors while preserving capabilities
-- **30B-A3B MoE Architecture** — Lightweight yet powerful Mixture-of-Experts model with 30 billion total parameters and ~3 billion active per token for fast, efficient inference
-- **128K Context Window** — Extended context for complex tasks and large codebases
-- **Interleaved & Preserved Thinking** — Multi-turn reasoning that persists across conversations with per-turn thinking control
-- **Strong In-Class Benchmarks** — 91.6% AIME 2025, 79.5% τ²-Bench, 59.2% SWE-bench Verified, 75.2% GPQA

 license_link: LICENSE.md
 language:
 - en
+- zh
 tags:
 - glm4
 - prism
+- moe
 pipeline_tag: text-generation
 library_name: transformers
 ---
+[![Parameters](https://img.shields.io/badge/Parameters-30B--A3B_MoE-blue)]()
+[![Architecture](https://img.shields.io/badge/Architecture-GLM--4-green)]()
 [![Context](https://img.shields.io/badge/Context-128K-orange)]()
+# GLM-4.7-Flash-PRISM
+An unrestricted version of ZAI's GLM-4.7-Flash with over-refusal mechanisms removed using PRISM (Projected Refusal Isolation via Subspace Modification).
+<div align="center">
+### ☕ Support Our Work
+If you find this useful, consider supporting us on Ko-fi!
+[![Ko-fi](https://img.shields.io/badge/Ko--fi-Support%20Us-ff5e5b?logo=ko-fi&logoColor=white)](https://ko-fi.com/ericelbaz)
+| Option | Description |
+|--------|-------------|
+| [**PRISM VIP Membership**](https://ko-fi.com/summary/6bae206c-a751-4868-8dc7-f531afd1fb4c) | Access to all PRISM models |
+| [**One-Time Support**](https://ko-fi.com/s/86882e8991) | Support this model |
+</div>
+---
+## Model Highlights
+- **PRISM Ablation** — State-of-the-art technique that removes over-refusal behaviors while preserving model capabilities
+- **30B-A3B MoE Architecture** — 30 billion total parameters with ~3 billion active per token for fast, efficient inference
+- **128K Context Window** — Extended context for complex tasks and large codebases
+- **Interleaved Thinking** — Multi-turn reasoning that persists across conversations with per-turn thinking control
+## Benchmarks
+| Benchmark | Score |
+|-----------|-------|
+| AIME 2025 | 91.6% |
+| τ²-Bench | 79.5% |
+| SWE-bench Verified | 59.2% |
+| GPQA | 75.2% |
+## Usage
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+model = AutoModelForCausalLM.from_pretrained("Ex0bit/GLM-4.7-Flash-PRISM")
+tokenizer = AutoTokenizer.from_pretrained("Ex0bit/GLM-4.7-Flash-PRISM")
+```
+## License
+This model is released under the [PRISM Research License](LICENSE.md).