Instructions to use zerofata/L3.3-GeneticLemonade-Unleashed-70B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zerofata/L3.3-GeneticLemonade-Unleashed-70B with Transformers:

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

pipe = pipeline("text-generation", model="zerofata/L3.3-GeneticLemonade-Unleashed-70B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zerofata/L3.3-GeneticLemonade-Unleashed-70B")
model = AutoModelForCausalLM.from_pretrained("zerofata/L3.3-GeneticLemonade-Unleashed-70B")
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

vLLM

How to use zerofata/L3.3-GeneticLemonade-Unleashed-70B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zerofata/L3.3-GeneticLemonade-Unleashed-70B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zerofata/L3.3-GeneticLemonade-Unleashed-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zerofata/L3.3-GeneticLemonade-Unleashed-70B

SGLang

How to use zerofata/L3.3-GeneticLemonade-Unleashed-70B 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 "zerofata/L3.3-GeneticLemonade-Unleashed-70B" \
    --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": "zerofata/L3.3-GeneticLemonade-Unleashed-70B",
		"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 "zerofata/L3.3-GeneticLemonade-Unleashed-70B" \
        --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": "zerofata/L3.3-GeneticLemonade-Unleashed-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zerofata/L3.3-GeneticLemonade-Unleashed-70B with Docker Model Runner:
```
docker model run hf.co/zerofata/L3.3-GeneticLemonade-Unleashed-70B
```

Amazing First Release

by John198 - opened Mar 2, 2025

Discussion

John198

Mar 2, 2025

I've been bouncing around a lot of Llama 3 models and this has found a nice balance of intelligence with 'less sloppy writing' (perhaps from the Sunfall in your mix?) Hope you get around to releasing the 4.5BPW of the "Final" version soon as it's been a while since I've been so excited to try something out.

zerofata

Owner Mar 2, 2025

Thank you!

I've just uploaded the 4.5bpw quant for the final version. Hope it lives up to expectations!

https://huggingface.co/zerofata/L3.3-GeneticLemonade-Final-70B-4.5bpw-h6-exl2

Sunfall acts almost like a pillar I think. Without it model coherence suffers unless I remove additional RP models, but that then provides another issue where the model feels too dry / assistant focused and its creative abilities suffer.

tachyon-beep

Apr 1, 2025

I came here to say the same thing about Final, its definitely one of the best models I've used, even at IQ3.

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