Instructions to use fasoo/llama3.1-financial-dedup with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fasoo/llama3.1-financial-dedup with Transformers:

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

pipe = pipeline("text-generation", model="fasoo/llama3.1-financial-dedup")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fasoo/llama3.1-financial-dedup")
model = AutoModelForCausalLM.from_pretrained("fasoo/llama3.1-financial-dedup")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fasoo/llama3.1-financial-dedup with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fasoo/llama3.1-financial-dedup"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fasoo/llama3.1-financial-dedup",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/fasoo/llama3.1-financial-dedup

SGLang

How to use fasoo/llama3.1-financial-dedup 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 "fasoo/llama3.1-financial-dedup" \
    --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": "fasoo/llama3.1-financial-dedup",
		"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 "fasoo/llama3.1-financial-dedup" \
        --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": "fasoo/llama3.1-financial-dedup",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use fasoo/llama3.1-financial-dedup with Docker Model Runner:
```
docker model run hf.co/fasoo/llama3.1-financial-dedup
```

Model Card for Model ID

해당 모델은 금융 도메인 데이터 83만개의 샘플에 대하여 추가학습한 모델입니다.

Llama 3.1 8B base 모델에서 학습이 진행되었으며, 그 외 추가적인 instruction tuning은 수행되지 않았습니다.

또한, 이 모델은 과학기술정보통신부·광주광역시가 공동 지원한 ‘인공지능 중심 산업융합 집적단지 조성사업’으로 지원을 받아 개발되었습니다.

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

Developed by: fasoo
Model type: Causal Language Model
Language(s) (NLP): English, Korean
License: [More Information Needed]
Finetuned from model: Llama 3.1 8B

Model Sources [optional]

Paper [optional]: [More Information Needed]

Uses

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fasoo/llama3.1-financial-dedup")
model = AutoModelForCausalLM.from_pretrained("fasoo/llama3.1-financial-dedup")

Environmental Impact

Hardware Type: NVIDIA H100 80GB HBM3
Compute Region: Gwangju, South Korea

Downloads last month: 1

Safetensors

Model size

8B params

Tensor type

F32