Instructions to use lemon07r/Gemma-2-Ataraxy-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lemon07r/Gemma-2-Ataraxy-9B with Transformers:

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

pipe = pipeline("text-generation", model="lemon07r/Gemma-2-Ataraxy-9B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lemon07r/Gemma-2-Ataraxy-9B")
model = AutoModelForCausalLM.from_pretrained("lemon07r/Gemma-2-Ataraxy-9B", device_map="auto")
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 lemon07r/Gemma-2-Ataraxy-9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lemon07r/Gemma-2-Ataraxy-9B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lemon07r/Gemma-2-Ataraxy-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lemon07r/Gemma-2-Ataraxy-9B

SGLang

How to use lemon07r/Gemma-2-Ataraxy-9B 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 "lemon07r/Gemma-2-Ataraxy-9B" \
    --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": "lemon07r/Gemma-2-Ataraxy-9B",
		"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 "lemon07r/Gemma-2-Ataraxy-9B" \
        --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": "lemon07r/Gemma-2-Ataraxy-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lemon07r/Gemma-2-Ataraxy-9B with Docker Model Runner:
```
docker model run hf.co/lemon07r/Gemma-2-Ataraxy-9B
```

KoboldCPP site not working for Gemma-2-Ataraxy-9B! Please fix this!

by OrbitalZix - opened Aug 25, 2024

Discussion

OrbitalZix

Aug 25, 2024

•

edited Aug 25, 2024

The site isn't working! Not sure if it was supposed to be temporary? @lemon07r

OrbitalZix changed discussion status to closed Aug 25, 2024

OrbitalZix changed discussion status to open Aug 25, 2024

OrbitalZix changed discussion title from KoboldCPP site not working for Gemma-2-Atraxy-9B! Please fix this! to KoboldCPP site not working for Gemma-2-Ataraxy-9B! Please fix this! Aug 25, 2024

lemon07r

Owner Aug 25, 2024

The site isn't working! Not sure if it was supposed to be temporary? @lemon07r

Sorry looks like the cloudflare tunnel or my PC died :(. I won't be home to fix this until late tomorrow night or the day after since I'm away visiting family.

OrbitalZix

Aug 25, 2024

It's alright, thank you for replying back! And enjoy your time with your family :)

lemon07r

Owner Aug 27, 2024

Ive returned home, looks like PC crashed or something, it was still running but unresponsive. Was going to host it for one more night but got too tired to fixed it. Sadly since Im home now, my pc will be in use, I wont be able to host this anymore.

lemon07r changed discussion status to closed Aug 27, 2024

OrbitalZix

Aug 27, 2024

•

edited Aug 28, 2024

Are there sites that I can visit that use this model? And if not how can I use this myself on koboldcpp? @lemon07r

OrbitalZix

Aug 28, 2024

Sorry for asking so many questions, sorta new to this

lemon07r

Owner Aug 28, 2024

Are there sites that I can visit that use this model? And if not how can I use this myself on koboldcpp? @lemon07r

You can load it yourself with koboldcpp, its extremely easy and beginner friendly. Just find and download a GGUF of the models you like, then load it up with kcpp. https://github.com/LostRuins/koboldcpp/releases

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