Instructions to use beomi/KoAlpaca-Polyglot-5.8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use beomi/KoAlpaca-Polyglot-5.8B with Transformers:

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

pipe = pipeline("text-generation", model="beomi/KoAlpaca-Polyglot-5.8B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("beomi/KoAlpaca-Polyglot-5.8B")
model = AutoModelForCausalLM.from_pretrained("beomi/KoAlpaca-Polyglot-5.8B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use beomi/KoAlpaca-Polyglot-5.8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "beomi/KoAlpaca-Polyglot-5.8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "beomi/KoAlpaca-Polyglot-5.8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/beomi/KoAlpaca-Polyglot-5.8B

SGLang

How to use beomi/KoAlpaca-Polyglot-5.8B 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 "beomi/KoAlpaca-Polyglot-5.8B" \
    --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": "beomi/KoAlpaca-Polyglot-5.8B",
		"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 "beomi/KoAlpaca-Polyglot-5.8B" \
        --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": "beomi/KoAlpaca-Polyglot-5.8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use beomi/KoAlpaca-Polyglot-5.8B with Docker Model Runner:
```
docker model run hf.co/beomi/KoAlpaca-Polyglot-5.8B
```

Update @ 2023.06.01

Add Safetensor sharded model weight (max shard = 1GB)

KoAlpaca-Polyglot-5.8B (v1.1b)

This model is a fine-tuned version of EleutherAI/polyglot-ko-5.8b on a KoAlpaca Dataset v1.1b

Detail Codes are available at KoAlpaca Github Repository

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 2
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 2.0
mixed_precision_training: Native AMP

Framework versions

Transformers 4.29.0.dev0
Pytorch 2.0.0+cu117
Datasets 2.10.1
Tokenizers 0.13.2

Downloads last month: 1,173

Safetensors

Model size

6B params

Tensor type

F16

F32

BOOL

Model tree for beomi/KoAlpaca-Polyglot-5.8B

Base model

EleutherAI/polyglot-ko-5.8b

Finetuned

(7)

this model

Adapters

40 models

Finetunes

1 model

beomi
/

KoAlpaca-Polyglot-5.8B

KoAlpaca-Polyglot-5.8B (v1.1b)

Training procedure

Training hyperparameters

Framework versions

Model tree for beomi/KoAlpaca-Polyglot-5.8B

Spaces using beomi/KoAlpaca-Polyglot-5.8B 40