Instructions to use Keynote-Technology/KAI-7B-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Keynote-Technology/KAI-7B-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="Keynote-Technology/KAI-7B-v0.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Keynote-Technology/KAI-7B-v0.1")
model = AutoModelForCausalLM.from_pretrained("Keynote-Technology/KAI-7B-v0.1")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Keynote-Technology/KAI-7B-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Keynote-Technology/KAI-7B-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Keynote-Technology/KAI-7B-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Keynote-Technology/KAI-7B-v0.1

SGLang

How to use Keynote-Technology/KAI-7B-v0.1 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 "Keynote-Technology/KAI-7B-v0.1" \
    --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": "Keynote-Technology/KAI-7B-v0.1",
		"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 "Keynote-Technology/KAI-7B-v0.1" \
        --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": "Keynote-Technology/KAI-7B-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Keynote-Technology/KAI-7B-v0.1 with Docker Model Runner:
```
docker model run hf.co/Keynote-Technology/KAI-7B-v0.1
```

Dataset Size

by aslawliet - opened Nov 26, 2023

Discussion

aslawliet

Nov 26, 2023

Can you tell me about the dataset size and sampling methods?

PlanetDOGE

Keynote Technology org Dec 2, 2023

One of the datasets used to train this model, PLANE-2K, has a size of 2 thousand rows (1.8 megabytes). You can use pretty much any sampling method you need as long as you have the appropriate tools.
https://huggingface.co/datasets/Keynote-Technology/PLANE-2K

aslawliet

Dec 2, 2023

I meant the size of data you picked up from RedPajama-Data-v2?

PlanetDOGE

Keynote Technology org Dec 2, 2023

•

edited Dec 2, 2023

The size that I used to train this model was close to 900,000 rows, a size equivalent to 4.41GB

PlanetDOGE

Keynote Technology org Dec 2, 2023

I sampled randomly in no particular order.

PlanetDOGE changed discussion status to closed Dec 16, 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