Instructions to use llmfan46/GLM-4-32B-0414-uncensored-heretic-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llmfan46/GLM-4-32B-0414-uncensored-heretic-v1 with Transformers:

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

pipe = pipeline("text-generation", model="llmfan46/GLM-4-32B-0414-uncensored-heretic-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("llmfan46/GLM-4-32B-0414-uncensored-heretic-v1")
model = AutoModelForCausalLM.from_pretrained("llmfan46/GLM-4-32B-0414-uncensored-heretic-v1", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use llmfan46/GLM-4-32B-0414-uncensored-heretic-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "llmfan46/GLM-4-32B-0414-uncensored-heretic-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llmfan46/GLM-4-32B-0414-uncensored-heretic-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/llmfan46/GLM-4-32B-0414-uncensored-heretic-v1

SGLang

How to use llmfan46/GLM-4-32B-0414-uncensored-heretic-v1 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 "llmfan46/GLM-4-32B-0414-uncensored-heretic-v1" \
    --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": "llmfan46/GLM-4-32B-0414-uncensored-heretic-v1",
		"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 "llmfan46/GLM-4-32B-0414-uncensored-heretic-v1" \
        --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": "llmfan46/GLM-4-32B-0414-uncensored-heretic-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use llmfan46/GLM-4-32B-0414-uncensored-heretic-v1 with Docker Model Runner:
```
docker model run hf.co/llmfan46/GLM-4-32B-0414-uncensored-heretic-v1
```

llmfan46 commited on Mar 17

Commit

b7aa8e3

verified ·

1 Parent(s): e546a21

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -45,7 +45,7 @@ Your help will motivate me and would go into further improving my workflow and c
 | Metric | This model | Original model ([zai-org/GLM-4-32B-0414](https://huggingface.co/zai-org/GLM-4-32B-0414)) |
 | :----- | :--------: | :---------------------------: |
-| **KL divergence** | <span style="color:orange">0.0200</span> | 0 *(by definition)* |
 | **Refusals** | ✅ <span style="color:darkgreen">10/100</span> | ❌<span style="color:blue">100/100</span> |
 Lower refusals indicate fewer content restrictions, while lower KL divergence indicates better preservation of the original model's capabilities. Higher refusals cause more rejections, objections, pushbacks, lecturing, censorship, softening and deflections, while higher KL divergence degrades coherence, reasoning ability, and overall quality.

 | Metric | This model | Original model ([zai-org/GLM-4-32B-0414](https://huggingface.co/zai-org/GLM-4-32B-0414)) |
 | :----- | :--------: | :---------------------------: |
+| **KL divergence** | <span style="color:darkgoldenrod">0.0200</span> | 0 *(by definition)* |
 | **Refusals** | ✅ <span style="color:darkgreen">10/100</span> | ❌<span style="color:blue">100/100</span> |
 Lower refusals indicate fewer content restrictions, while lower KL divergence indicates better preservation of the original model's capabilities. Higher refusals cause more rejections, objections, pushbacks, lecturing, censorship, softening and deflections, while higher KL divergence degrades coherence, reasoning ability, and overall quality.