Instructions to use NeverSleep/Noromaid-13b-v0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NeverSleep/Noromaid-13b-v0.2 with Transformers:

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

pipe = pipeline("text-generation", model="NeverSleep/Noromaid-13b-v0.2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NeverSleep/Noromaid-13b-v0.2")
model = AutoModelForCausalLM.from_pretrained("NeverSleep/Noromaid-13b-v0.2")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use NeverSleep/Noromaid-13b-v0.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NeverSleep/Noromaid-13b-v0.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NeverSleep/Noromaid-13b-v0.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NeverSleep/Noromaid-13b-v0.2

SGLang

How to use NeverSleep/Noromaid-13b-v0.2 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 "NeverSleep/Noromaid-13b-v0.2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NeverSleep/Noromaid-13b-v0.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "NeverSleep/Noromaid-13b-v0.2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NeverSleep/Noromaid-13b-v0.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NeverSleep/Noromaid-13b-v0.2 with Docker Model Runner:
```
docker model run hf.co/NeverSleep/Noromaid-13b-v0.2
```

20B

by R136a1 - opened Dec 17, 2023

Discussion

R136a1

Dec 17, 2023

I really like the Noromaid-20b-v0.1.1 and want to try the v0.2

IkariDev

NeverSleep org Dec 17, 2023

We dont know if its worth it making a 20b for v0.2, it costs us money to make this stuff. We will need more feedback on this version and then we can decide if its worth it making a 20b for v0.2.

xss

Jan 9, 2024

What does it cost? A few hundred dollars? Ever thought about a Patreon?

Undi95

NeverSleep org Jan 9, 2024

What does it cost? A few hundred dollars? Ever thought about a Patreon?

We run on Kofi donation and our own money, here is the cost for today training for exemple (we do an entire new try on the 8x7b atm)

It go fast. New version soon of 7B, 13B and 8x7B if all work out, stay tuned.
And maybe 20B, if we have the time haha

xss

Jan 9, 2024

Oh, nice. I didn't notice that in your profile. I made a small donation to help you along.

010O11

Jan 9, 2024

Is there any interest or thought or kind of effort towards MoE 2x ??? Does 2x make sense for you guys?

Undi95

NeverSleep org Jan 9, 2024

Is there any interest or thought or kind of effort towards MoE 2x ??? Does 2x make sense for you guys?

We can only does MoE of power of 2, but not two.
So 4, 8, 16, 32...
That's how it work.

010O11

Jan 9, 2024

Sry for lame question and thanks for response

Undi95

NeverSleep org Jan 9, 2024

Sry for lame question and thanks for response

All good!

010O11

Jan 11, 2024

once more again me ... I hope I don't anoy with my lameness, but for example Maxime Labonne speaks about that 2x mixes can be done... here with phi.. https://twitter.com/maximelabonne/status/1744867841436700850

and also Cros Nastasi didn't deny it here https://huggingface.co/dillfrescott/sonya-7b-x8-MoE/discussions/1

What am I missing? (I am betting on your patience with me, knowing its not infinite....)

Undi95

NeverSleep org Jan 11, 2024

You don't miss anything, maybe it's possible now, but llama.cpp just blocked it before. Need to check

xss

Jan 11, 2024

Doesn't a MoE imply expert routing/balancing and mixing? With two wouldn't you either have no balancing (it always chose both experts to mix) or no mixing (if it could only choose one to route to per token). At that point isn't a larger single model more simple and has the benefit of monolithic scale? I mean I'm not qualified to judge that tweet but I guess I don't understand what is going on either.

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