Instructions to use oilbread/KoAlpaca-Polyglot-5.8B-10epoch-eosend with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use oilbread/KoAlpaca-Polyglot-5.8B-10epoch-eosend with Transformers:

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

pipe = pipeline("text-generation", model="oilbread/KoAlpaca-Polyglot-5.8B-10epoch-eosend")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("oilbread/KoAlpaca-Polyglot-5.8B-10epoch-eosend")
model = AutoModelForCausalLM.from_pretrained("oilbread/KoAlpaca-Polyglot-5.8B-10epoch-eosend")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use oilbread/KoAlpaca-Polyglot-5.8B-10epoch-eosend with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "oilbread/KoAlpaca-Polyglot-5.8B-10epoch-eosend"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "oilbread/KoAlpaca-Polyglot-5.8B-10epoch-eosend",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/oilbread/KoAlpaca-Polyglot-5.8B-10epoch-eosend

SGLang

How to use oilbread/KoAlpaca-Polyglot-5.8B-10epoch-eosend 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 "oilbread/KoAlpaca-Polyglot-5.8B-10epoch-eosend" \
    --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": "oilbread/KoAlpaca-Polyglot-5.8B-10epoch-eosend",
		"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 "oilbread/KoAlpaca-Polyglot-5.8B-10epoch-eosend" \
        --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": "oilbread/KoAlpaca-Polyglot-5.8B-10epoch-eosend",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use oilbread/KoAlpaca-Polyglot-5.8B-10epoch-eosend with Docker Model Runner:
```
docker model run hf.co/oilbread/KoAlpaca-Polyglot-5.8B-10epoch-eosend
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

{ "_name_or_path": "beomi/KoAlpaca-Polyglot-5.8B", "architectures": [
"GPTNeoXForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"classifier_dropout": 0.1,
"eos_token_id": 0,
"hidden_act": "gelu",
"hidden_dropout": 0.0,
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 16384,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 2048,
"model_type": "gpt_neox",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_steps": "global_step320000",
"rope_scaling": null,
"rotary_emb_base": 10000,
"rotary_pct": 0.25,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.31.0",
"use_cache": true,
"use_parallel_residual": true,
"vocab_size": 30080
}

change data eos <|endtext|> to <끝>

Downloads last month: 4