Instructions to use ockerman0/AnubisLemonade-70B-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ockerman0/AnubisLemonade-70B-v1 with Transformers:

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

pipe = pipeline("text-generation", model="ockerman0/AnubisLemonade-70B-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ockerman0/AnubisLemonade-70B-v1")
model = AutoModelForCausalLM.from_pretrained("ockerman0/AnubisLemonade-70B-v1")
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 ockerman0/AnubisLemonade-70B-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ockerman0/AnubisLemonade-70B-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": "ockerman0/AnubisLemonade-70B-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ockerman0/AnubisLemonade-70B-v1

SGLang

How to use ockerman0/AnubisLemonade-70B-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 "ockerman0/AnubisLemonade-70B-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": "ockerman0/AnubisLemonade-70B-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 "ockerman0/AnubisLemonade-70B-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": "ockerman0/AnubisLemonade-70B-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ockerman0/AnubisLemonade-70B-v1 with Docker Model Runner:
```
docker model run hf.co/ockerman0/AnubisLemonade-70B-v1
```

Nice!

by yano2mch - opened Jul 5, 2025

Discussion

yano2mch

Jul 5, 2025

Trying out various models and all the Anubis and Lemonade models all seem to do quite nicely! Merged seems to work decently too.

ockerman0

Owner Jul 5, 2025

Glad to see you're enjoying it! Personally I wasn't very convinced by this merge so I may try a different config soon.

yano2mch

Jul 5, 2025

Glad to see you're enjoying it! Personally I wasn't very convinced by this merge so I may try a different config soon.

Perhaps. The lines of where one model begins and ends is difficult to know, i am basically treating Anubis, AnubisLemonade and GeneticLemonade as the same model(s), they are so close to eachother.

yano2mch

Jul 7, 2025

Well used this a bit more. Got to say this feels like the most over-eager model to want to do NSFW content, and gets horny at really raunchy ideas.

Okay to be honest I'm doing ERP so raunchy is expected; But I'd say this model actually gets off on it.

ockerman0

Owner Jul 7, 2025

That certainly is interesting... I'm not sure whether to interpret that as a good thing or a bad thing!

yano2mch

Jul 8, 2025

•

edited Jul 8, 2025

That certainly is interesting... I'm not sure whether to interpret that as a good thing or a bad thing!

I'd say good. Though the model feels a little submissive.

Who knows maybe i'm just too kinky :P
But i'll still be interested in any changes you make when you redo it.

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