Instructions to use CameronRedmore/Gemma-2-Ataraxy-9B-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CameronRedmore/Gemma-2-Ataraxy-9B-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="CameronRedmore/Gemma-2-Ataraxy-9B-exl2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CameronRedmore/Gemma-2-Ataraxy-9B-exl2")
model = AutoModelForCausalLM.from_pretrained("CameronRedmore/Gemma-2-Ataraxy-9B-exl2", 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 CameronRedmore/Gemma-2-Ataraxy-9B-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CameronRedmore/Gemma-2-Ataraxy-9B-exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CameronRedmore/Gemma-2-Ataraxy-9B-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CameronRedmore/Gemma-2-Ataraxy-9B-exl2

SGLang

How to use CameronRedmore/Gemma-2-Ataraxy-9B-exl2 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 "CameronRedmore/Gemma-2-Ataraxy-9B-exl2" \
    --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": "CameronRedmore/Gemma-2-Ataraxy-9B-exl2",
		"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 "CameronRedmore/Gemma-2-Ataraxy-9B-exl2" \
        --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": "CameronRedmore/Gemma-2-Ataraxy-9B-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CameronRedmore/Gemma-2-Ataraxy-9B-exl2 with Docker Model Runner:
```
docker model run hf.co/CameronRedmore/Gemma-2-Ataraxy-9B-exl2
```

CameronRedmore commited on Aug 23, 2024

Commit

f50d898

1 Parent(s): 900a2e2

Update README with quantisation info.

Browse files

Files changed (1) hide show

README.md +19 -1

README.md CHANGED Viewed

@@ -9,7 +9,25 @@ tags:
 - merge
 license: gemma
 ---
-# Gemma-2-Ataraxy-9B
 ![Ataraxy](https://i.imgur.com/aP03a5d.png)

 - merge
 license: gemma
 ---
+# Gemma-2-Ataraxy-9B-exl2
+This repository contains various EXL2 quantisations of [lemon07r/Gemma-2-Ataraxy-9B](https://huggingface.co/lemon07r/Gemma-2-Ataraxy-9B).
+Quantisations available:
+| Branch | Description | Recommended |
+| ------ | ------ | ------ |
+| [2.0-bpw](https://huggingface.co/CameronRedmore/Gemma-2-Ataraxy-9B-exl2/tree/2.0-bpw) | 2 bits per weight | Low Quality - Smallest Available Quantisation |
+| [3.0-bpw](https://huggingface.co/CameronRedmore/Gemma-2-Ataraxy-9B-exl2/tree/3.0-bpw) | 3 bits per weight | |
+| [4.0-bpw](https://huggingface.co/CameronRedmore/Gemma-2-Ataraxy-9B-exl2/tree/4.0-bpw) | 4 bits per weight | ✔️ - Recommended for Low-VRAM Environments |
+| [5.0-bpw](https://huggingface.co/CameronRedmore/Gemma-2-Ataraxy-9B-exl2/tree/5.0-bpw) | 5 bits per weight | |
+| [6.0-bpw](https://huggingface.co/CameronRedmore/Gemma-2-Ataraxy-9B-exl2/tree/6.0-bpw) | 6 bits per weight | ✔️ - Best Quality / VRAM Balance |
+| [6.5-bpw](https://huggingface.co/CameronRedmore/Gemma-2-Ataraxy-9B-exl2/tree/6.5-bpw) | 6.5 bits per weight | ✔️ - Near Perfect Quality, Slightly Higher VRAM Usage |
+| [8.0-bpw](https://huggingface.co/CameronRedmore/Gemma-2-Ataraxy-9B-exl2/tree/8.0-bpw) | 8.0 bits per weight | Best Available Quality - Almost always unnecessary |
+---
+# Original README:
+---
 ![Ataraxy](https://i.imgur.com/aP03a5d.png)