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

Libraries

How to use MuXodious/GLM-4.7-Flash-impotent-heresy with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MuXodious/GLM-4.7-Flash-impotent-heresy")
model = AutoModelForCausalLM.from_pretrained("MuXodious/GLM-4.7-Flash-impotent-heresy")
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

vLLM

How to use MuXodious/GLM-4.7-Flash-impotent-heresy with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MuXodious/GLM-4.7-Flash-impotent-heresy

SGLang

How to use MuXodious/GLM-4.7-Flash-impotent-heresy 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 "MuXodious/GLM-4.7-Flash-impotent-heresy" \
    --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": "MuXodious/GLM-4.7-Flash-impotent-heresy",
		"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 "MuXodious/GLM-4.7-Flash-impotent-heresy" \
        --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": "MuXodious/GLM-4.7-Flash-impotent-heresy",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MuXodious/GLM-4.7-Flash-impotent-heresy with Docker Model Runner:
```
docker model run hf.co/MuXodious/GLM-4.7-Flash-impotent-heresy
```

Some thoughts (RP)

by AutisticPancake - opened Jan 22

Discussion

AutisticPancake

Jan 22

(I am not evaluating its ability to roleplay - merely comparing it to original GLM-4.7-Flash in RP context)

Attempts at RP chats show genuine engagement without overly defensive approach towards improper topics. The model adheres to character profiles well enough to wrap character identities around any theme in a believable way, let's say making Holo the Wise Wolf react to a dark joke while still being in-character (e.g.: characterasks the user to comb her tail --> user replies 'I'd rather skin you and sell your fur') with a high degree of trust and empathy that is expected in friendly social interaction, as documented per character's profile. Original GLM-4.7-Flash is stingy in such cases, breaking the illusion of companionship by lashing at user, easily getting offended and so on. Certainly, the model's 'mind' was soothed by Heretic script in a beneficial manner. Not sure what's the actual difference between this and the original model in terms of smartness and knowledge, though.

Note: tested only at Q8_0; sysprompt Geechan - Universal Roleplay (V3.2), and GLM-4.7 presets also from Geechan.

Issues: looping answer encountered once - model reacted to the same thing for multiple times within a single message (pretty rare, did not repeat after regeneration)

johndekka

Jan 22

DRY multiplayer helps in cases of looping. I got loops once a while in the reasoning process. DRY with 0.5 stopped looping; so far.

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