Instructions to use jeiku/Average_Normie_v3.69_8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jeiku/Average_Normie_v3.69_8B with Transformers:

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

pipe = pipeline("text-generation", model="jeiku/Average_Normie_v3.69_8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("jeiku/Average_Normie_v3.69_8B")
model = AutoModelForMultimodalLM.from_pretrained("jeiku/Average_Normie_v3.69_8B")
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

vLLM

How to use jeiku/Average_Normie_v3.69_8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jeiku/Average_Normie_v3.69_8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jeiku/Average_Normie_v3.69_8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jeiku/Average_Normie_v3.69_8B

SGLang

How to use jeiku/Average_Normie_v3.69_8B 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 "jeiku/Average_Normie_v3.69_8B" \
    --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": "jeiku/Average_Normie_v3.69_8B",
		"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 "jeiku/Average_Normie_v3.69_8B" \
        --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": "jeiku/Average_Normie_v3.69_8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jeiku/Average_Normie_v3.69_8B with Docker Model Runner:
```
docker model run hf.co/jeiku/Average_Normie_v3.69_8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Average Normie v3.69

The third step in the Average Normie line sees a very big step toward NSFW content, while also allowing for steerability through example messages and first message editing. If you do not want an NSFW conversation, I highly recommend removing all NSFW content from your character card and examples, because this model will lean into that use case very heavily.

With that said, I am seeing a fair bit of flexibility with first message editing and example message editing. This model will take on the speech pattern that you set for it, so don't be discouraged if you need to modify the first message to get a better chat style.

The responses can be very human-like and impressive, and the model will gladly stick to any writing style you direct it to use. If you want shorter responses, then prompt it for shorter responses in your system prompt or character card. Don't be afraid to prompt the bot to alter its speech patterns, it is very flexible.

I hope you guys like this model. Make sure your inference software is updated to the very latest version if you have any issues. Thanks for checking this one out!

🧩 Configuration

models:
  - model: cgato/L3-TheSpice-8b-v0.8.3
  - model: Sao10K/L3-8B-Stheno-v3.2
  - model: saishf/Aura-Uncensored-OAS-8B-L3
merge_method: model_stock
base_model: saishf/Aura-Uncensored-OAS-8B-L3
dtype: float16

Downloads last month: 6

Safetensors

Model size

8B params

Tensor type

F16

Model tree for jeiku/Average_Normie_v3.69_8B

Merges

1 model

Quantizations

5 models