Instructions to use cgus/NemoMix-Unleashed-12B-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cgus/NemoMix-Unleashed-12B-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="cgus/NemoMix-Unleashed-12B-exl2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cgus/NemoMix-Unleashed-12B-exl2")
model = AutoModelForCausalLM.from_pretrained("cgus/NemoMix-Unleashed-12B-exl2")
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 cgus/NemoMix-Unleashed-12B-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cgus/NemoMix-Unleashed-12B-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": "cgus/NemoMix-Unleashed-12B-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cgus/NemoMix-Unleashed-12B-exl2

SGLang

How to use cgus/NemoMix-Unleashed-12B-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 "cgus/NemoMix-Unleashed-12B-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": "cgus/NemoMix-Unleashed-12B-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 "cgus/NemoMix-Unleashed-12B-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": "cgus/NemoMix-Unleashed-12B-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cgus/NemoMix-Unleashed-12B-exl2 with Docker Model Runner:
```
docker model run hf.co/cgus/NemoMix-Unleashed-12B-exl2
```

cgus commited on Aug 28, 2024

Commit

8a13954

verified ·

1 Parent(s): b7a2ae6

Update README.md

Browse files

Files changed (1) hide show

README.md +15 -2

README.md CHANGED Viewed

@@ -1,11 +1,24 @@
 ---
-base_model: []
 library_name: transformers
 tags:
 - mergekit
 - merge
 ---
 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6550b16f7490049d6237f200/zYBXSewLbIxWHZdB3oEHs.jpeg)
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6550b16f7490049d6237f200/eRwPcd9Ox03hn_WRnsotj.png)

 ---
 library_name: transformers
 tags:
 - mergekit
 - merge
+base_model: MarinaraSpaghetti/NemoMix-Unleashed-12B
 ---
+# NemoMix-Unleashed-12B-exl2
+Original model: [NemoMix-Unleashed-12B](https://huggingface.co/MarinaraSpaghetti/NemoMix-Unleashed-12B)
+Creator: [MarinaraSpaghetti](https://huggingface.co/MarinaraSpaghetti)
+## Quants
+[4bpw h6 (main)](https://huggingface.co/cgus/NemoMix-Unleashed-12B-exl2/tree/main)
+[4.5bpw h6](https://huggingface.co/cgus/NemoMix-Unleashed-12B-exl2/tree/4.5bpw-h6)
+[5bpw h6](https://huggingface.co/cgus/NemoMix-Unleashed-12B-exl2/tree/5bpw-h6)
+[6bpw h6](https://huggingface.co/cgus/NemoMix-Unleashed-12B-exl2/tree/6bpw-h6)
+[8bpw h8](https://huggingface.co/cgus/NemoMix-Unleashed-12B-exl2/tree/8bpw-h8)
+## Quantization notes
+Made with Exllamav2 0.1.8 with the default dataset.
+# Original model card
 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6550b16f7490049d6237f200/zYBXSewLbIxWHZdB3oEHs.jpeg)
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6550b16f7490049d6237f200/eRwPcd9Ox03hn_WRnsotj.png)