Instructions to use KISTI-KONI/KONI-Llama3-8B-20240630 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KISTI-KONI/KONI-Llama3-8B-20240630 with Transformers:

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

pipe = pipeline("text-generation", model="KISTI-KONI/KONI-Llama3-8B-20240630")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KISTI-KONI/KONI-Llama3-8B-20240630")
model = AutoModelForCausalLM.from_pretrained("KISTI-KONI/KONI-Llama3-8B-20240630")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use KISTI-KONI/KONI-Llama3-8B-20240630 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KISTI-KONI/KONI-Llama3-8B-20240630"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KISTI-KONI/KONI-Llama3-8B-20240630",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/KISTI-KONI/KONI-Llama3-8B-20240630

SGLang

How to use KISTI-KONI/KONI-Llama3-8B-20240630 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 "KISTI-KONI/KONI-Llama3-8B-20240630" \
    --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": "KISTI-KONI/KONI-Llama3-8B-20240630",
		"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 "KISTI-KONI/KONI-Llama3-8B-20240630" \
        --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": "KISTI-KONI/KONI-Llama3-8B-20240630",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use KISTI-KONI/KONI-Llama3-8B-20240630 with Docker Model Runner:
```
docker model run hf.co/KISTI-KONI/KONI-Llama3-8B-20240630
```

KONI-Llama3-8B-20240630 / model-00004-of-00004.safetensors

yangdonghun3

Upload 10 files

12e3b91 verified almost 2 years ago

Download

History Blame Contribute Delete

1.17 GB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: 11538c94d8683a8222dee026a92b686c7feb24100cbe6ea064f35f11a8bf2f69
Size of remote file:: 1.17 GB
SHA256:: afbf5d61131ea1de8a6a402b812a95a4f165cdf20ab62a7298683b5650b8835c

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.