Instructions to use schnapper79/lumikabra-123B_v0.4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use schnapper79/lumikabra-123B_v0.4 with Transformers:

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

pipe = pipeline("text-generation", model="schnapper79/lumikabra-123B_v0.4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("schnapper79/lumikabra-123B_v0.4")
model = AutoModelForCausalLM.from_pretrained("schnapper79/lumikabra-123B_v0.4")
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 schnapper79/lumikabra-123B_v0.4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "schnapper79/lumikabra-123B_v0.4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "schnapper79/lumikabra-123B_v0.4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/schnapper79/lumikabra-123B_v0.4

SGLang

How to use schnapper79/lumikabra-123B_v0.4 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 "schnapper79/lumikabra-123B_v0.4" \
    --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": "schnapper79/lumikabra-123B_v0.4",
		"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 "schnapper79/lumikabra-123B_v0.4" \
        --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": "schnapper79/lumikabra-123B_v0.4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use schnapper79/lumikabra-123B_v0.4 with Docker Model Runner:
```
docker model run hf.co/schnapper79/lumikabra-123B_v0.4
```

Compared to Luminum?

by lightning-missile - opened Oct 9, 2024

Discussion

lightning-missile

Oct 9, 2024

Hi,
I’ve downloaded lumikabra-123B_v0.4.Q8_0.gguf from here (https://huggingface.co/mradermacher/lumikabra-123B_v0.4-GGUF/tree/main) and started experimenting with it. So far, I haven’t really noticed any difference compared to Luminum. I’m mainly using it for creative writing (like: Write a story about a battle to the death between Jeff, who controls fire, and John, who controls water).
But this is the first time I’m using it, so maybe I’ll notice some differences as I go. Could you explain what improvements you meant? And if you have any good storytelling prompts, that’d be great too!
Thanks!

schnapper79

Owner Oct 9, 2024

In my personal experience Luminum tended to be pretty horny sometimes (I guess because of the Magnum in its heritage). I believe adding some Tess helped with knowledge against horniness. As you can see I played with the merge settings, and I feel each model is a little different in character (as far as a model can have a personality of course).

lightning-missile

Oct 9, 2024

In my personal experience Luminum tended to be pretty horny sometimes (I guess because of the Magnum in its heritage). I believe adding some Tess helped with knowledge against horniness. As you can see I played with the merge settings, and I feel each model is a little different in character (as far as a model can have a personality of course).

Oh I see. I thought you wanted more hornyness when you say "missed some spice, another sauce". I'll compare ERP and non ERP senarios later on.

schnapper79

Owner Oct 9, 2024

Oh am not against spice. Magnum has a pretty in your face kind of horniness. I was looking for a model that goes into every dungeon with you, but in a creative, entertaining way.

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