Instructions to use TomGrc/FusionNet_7Bx2_MoE_14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TomGrc/FusionNet_7Bx2_MoE_14B with Transformers:

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

pipe = pipeline("text-generation", model="TomGrc/FusionNet_7Bx2_MoE_14B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TomGrc/FusionNet_7Bx2_MoE_14B")
model = AutoModelForCausalLM.from_pretrained("TomGrc/FusionNet_7Bx2_MoE_14B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TomGrc/FusionNet_7Bx2_MoE_14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TomGrc/FusionNet_7Bx2_MoE_14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TomGrc/FusionNet_7Bx2_MoE_14B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TomGrc/FusionNet_7Bx2_MoE_14B

SGLang

How to use TomGrc/FusionNet_7Bx2_MoE_14B 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 "TomGrc/FusionNet_7Bx2_MoE_14B" \
    --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": "TomGrc/FusionNet_7Bx2_MoE_14B",
		"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 "TomGrc/FusionNet_7Bx2_MoE_14B" \
        --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": "TomGrc/FusionNet_7Bx2_MoE_14B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TomGrc/FusionNet_7Bx2_MoE_14B with Docker Model Runner:
```
docker model run hf.co/TomGrc/FusionNet_7Bx2_MoE_14B
```

prompt format

by KnutJaegersberg - opened Jan 14, 2024

Discussion

KnutJaegersberg

Jan 14, 2024

what prompt format does the model expect?

KnutJaegersberg

Jan 14, 2024

@LoneStriker will you make exl versions?

LoneStriker

Jan 14, 2024

Yup, already made them earlier here:
https://huggingface.co/models?sort=trending&search=lonestriker+FusionNet_7Bx2_MoE_14B

wukongai

Jan 15, 2024

Yup, already made them earlier here:
https://huggingface.co/models?sort=trending&search=lonestriker+FusionNet_7Bx2_MoE_14B
@LoneStriker
would really appreciate a GGUF version for this model, thank you!

fblgit

Jan 16, 2024

Chatml will work good
Alpaca also.
Smart models behave well on any prompt, they are smart enough

KnutJaegersberg

Jan 16, 2024

Yes, yet I think by knowing the format the model was trained with, we can get a little more performance out of it, that's why I would like to know it. Might also have been a mixture, a dataset with different prompts.

umarbutler

Jan 31, 2024

@TomGrc Could we get your input on this, namely, what prompt format(s) the model was trained with and what format you would advise using?

TomGrc

Owner Jan 31, 2024

You are FusionNet, a large language model trained by Suqin Zhang, based on the Llama 2 architecture. You are a helpful assistant.

KnutJaegersberg changed discussion status to closed Jan 31, 2024

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