Instructions to use fangloveskari/ORCA_LLaMA_70B_QLoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fangloveskari/ORCA_LLaMA_70B_QLoRA with Transformers:

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

pipe = pipeline("text-generation", model="fangloveskari/ORCA_LLaMA_70B_QLoRA")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fangloveskari/ORCA_LLaMA_70B_QLoRA")
model = AutoModelForCausalLM.from_pretrained("fangloveskari/ORCA_LLaMA_70B_QLoRA", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fangloveskari/ORCA_LLaMA_70B_QLoRA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fangloveskari/ORCA_LLaMA_70B_QLoRA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fangloveskari/ORCA_LLaMA_70B_QLoRA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/fangloveskari/ORCA_LLaMA_70B_QLoRA

SGLang

How to use fangloveskari/ORCA_LLaMA_70B_QLoRA 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 "fangloveskari/ORCA_LLaMA_70B_QLoRA" \
    --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": "fangloveskari/ORCA_LLaMA_70B_QLoRA",
		"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 "fangloveskari/ORCA_LLaMA_70B_QLoRA" \
        --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": "fangloveskari/ORCA_LLaMA_70B_QLoRA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use fangloveskari/ORCA_LLaMA_70B_QLoRA with Docker Model Runner:
```
docker model run hf.co/fangloveskari/ORCA_LLaMA_70B_QLoRA
```

Data Repositories and Size of Dataset

by AIdinner - opened Sep 3, 2023

Discussion

AIdinner

Sep 3, 2023

Hi bro, could you please specify which repositories the ORCA and Dolphin Data you used come from and the total amount of your unpublished dataset? Thanks a lot!

fangloveskari

Owner Sep 3, 2023

OK. garage-bAInd/Open-Platypus, ehartford/dolphin: flan1m-alpaca-uncensored-deduped.jsonl, Open-Orca/OpenOrca:1M-GPT4-Augmented.parquet
The amount is around 50K.

AIdinner

Sep 3, 2023

Thank you for your detailed information!
However, I have another question that, you said in your model card that you selected 5% Dolphin Data and 7% OpenOrca which are 120K in total and how could the final amount be around 50K? I am not sure whether or not I misunderstood your comment and your model card.
looking forward to your reply!

fangloveskari

Owner Sep 3, 2023

Oh, I get that, It's a mistake and I forget to revise the readme, I first use 5% Dolphin and 7% OpenOrca mixed with Platypus for training , but found a inferior performance(which we guess replicate or similar data still exists), so I filter the remaining data again, and finally only ~1% Dolphin and ~1% OpenORCA data remained. I will update the ReadMe file later, sorry for that.

fangloveskari changed discussion status to closed Sep 4, 2023

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