Instructions to use wolfram/miqu-1-120b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wolfram/miqu-1-120b with Transformers:

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

pipe = pipeline("text-generation", model="wolfram/miqu-1-120b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("wolfram/miqu-1-120b")
model = AutoModelForCausalLM.from_pretrained("wolfram/miqu-1-120b")
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

vLLM

How to use wolfram/miqu-1-120b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wolfram/miqu-1-120b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wolfram/miqu-1-120b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wolfram/miqu-1-120b

SGLang

How to use wolfram/miqu-1-120b 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 "wolfram/miqu-1-120b" \
    --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": "wolfram/miqu-1-120b",
		"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 "wolfram/miqu-1-120b" \
        --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": "wolfram/miqu-1-120b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use wolfram/miqu-1-120b with Docker Model Runner:
```
docker model run hf.co/wolfram/miqu-1-120b
```

Guidance on GPU VRAM Split?

by nmitchko - opened Feb 7, 2024

Discussion

nmitchko

Feb 7, 2024

Hi,

Thank you for the merge, this is a very cool model with nice performance.

I am currently on 2xA40, is there an optimal VRAM split that will best optimize for performance? I am getting pretty slow TK/s, but I guess that's expected. Any tips would be interesting

wolfram

Owner Feb 9, 2024

I'm splitting 22,24 over 2x3090's 48 GB VRAM. I generally fill the second GPU completely and take as much as necessary from the first.

kikosama

Feb 26, 2024

I'm splitting 22,24 over 2x3090's 48 GB VRAM. I generally fill the second GPU completely and take as much as necessary from the first.

Are you talking about the quantized model or the full fp16 model? I assume the former?

nmitchko

Feb 27, 2024

Wolfram's got to be referring to a quantized version, perhaps the most aggressive quants?

nmitchko

Feb 27, 2024

To be clear I am also running a quant, but bpw 6.0

wolfram

Owner Feb 27, 2024

Yes, quantized. I run e. g. wolfram_miquliz-120b-v2.0-3.0bpw-h6-exl2 with a 22,24 GPU split for 4K context at 10 tokens/s.

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