Instructions to use fblgit/una-xaberius-34b-v1beta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fblgit/una-xaberius-34b-v1beta with Transformers:

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

pipe = pipeline("text-generation", model="fblgit/una-xaberius-34b-v1beta")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fblgit/una-xaberius-34b-v1beta")
model = AutoModelForCausalLM.from_pretrained("fblgit/una-xaberius-34b-v1beta")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use fblgit/una-xaberius-34b-v1beta with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fblgit/una-xaberius-34b-v1beta"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fblgit/una-xaberius-34b-v1beta",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/fblgit/una-xaberius-34b-v1beta

SGLang

How to use fblgit/una-xaberius-34b-v1beta 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 "fblgit/una-xaberius-34b-v1beta" \
    --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": "fblgit/una-xaberius-34b-v1beta",
		"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 "fblgit/una-xaberius-34b-v1beta" \
        --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": "fblgit/una-xaberius-34b-v1beta",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use fblgit/una-xaberius-34b-v1beta with Docker Model Runner:
```
docker model run hf.co/fblgit/una-xaberius-34b-v1beta
```

200K?

by brucethemoose - opened Dec 6, 2023

Discussion

brucethemoose

Dec 6, 2023

•

edited Dec 6, 2023

Would you consider training on the 200K model instead of base Yi? Even if the training context is much shorter, some of the long context performance seems to be preserved.

Also, is this a Lora or a native fintune? If the former, could you post the lora?

fblgit

Owner Dec 12, 2023

@brucethemoose
Raised
If u share the train script for the 200K i can give it a shot as it is right now, im not sure how to expand such a context.. the limit is 8xH100.. if thats not enough than I wont be able to run it.

brucethemoose

Dec 12, 2023

Oh it doesn't have to be trained natively at 200k, training at lower context still preserves some of the higher context.

That being said, the training repo you want is probably unsloth, which now has a DPO script and should save quite a bit of VRAM.

brucethemoose

Dec 12, 2023

•

edited Dec 12, 2023

Also, see this concise PEFT issue for LongLora, for higher quality training at long context:

https://github.com/huggingface/peft/issues/958

TBH I have no idea what Yi did on their end to train at such an extreme context.

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