Instructions to use mintaeng/small_fut_final with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mintaeng/small_fut_final with Transformers:

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

pipe = pipeline("text-generation", model="mintaeng/small_fut_final")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mintaeng/small_fut_final")
model = AutoModelForCausalLM.from_pretrained("mintaeng/small_fut_final")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use mintaeng/small_fut_final with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mintaeng/small_fut_final"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mintaeng/small_fut_final",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mintaeng/small_fut_final

SGLang

How to use mintaeng/small_fut_final 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 "mintaeng/small_fut_final" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mintaeng/small_fut_final",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "mintaeng/small_fut_final" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mintaeng/small_fut_final",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use mintaeng/small_fut_final with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mintaeng/small_fut_final to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mintaeng/small_fut_final to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mintaeng/small_fut_final to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="mintaeng/small_fut_final",
    max_seq_length=2048,
)

Docker Model Runner
How to use mintaeng/small_fut_final with Docker Model Runner:
```
docker model run hf.co/mintaeng/small_fut_final
```

FUT FUT CHAT BOT

오픈소스 모델에 LLM fine tuning 과 RAG 를 적용
풋살에 대한 관심이 높아지면서 수요 대비 입문자를 위한 정보 제공 서비스가 필요하다고 느껴 제작하게 됨
풋살 플랫폼에 사용되는 풋살 정보 도우미 챗봇
'해요체'로 답하며 문장 끝에 '얼마든지 물어보세요~ 풋풋~!' 을 출력함

HOW TO USE

  
  #!pip install transformers==4.40.0 accelerate
  import os
  import torch
  from transformers import AutoTokenizer, AutoModelForCausalLM
  
  model_id = 'Dongwookss/small_fut_final'
  
  tokenizer = AutoTokenizer.from_pretrained(model_id)
  model = AutoModelForCausalLM.from_pretrained(
      model_id,
      torch_dtype=torch.bfloat16,
      device_map="auto",
  )
  model.eval()

Query

from transformers import TextStreamer
PROMPT = '''Below is an instruction that describes a task. Write a response that appropriately completes the request.
제시하는 context에서만 대답하고 context에 없는 내용은 모르겠다고 대답해'''

messages = [
    {"role": "system", "content": f"{PROMPT}"},
    {"role": "user", "content": f"{instruction}"}
    ]

input_ids = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

terminators = [
    tokenizer.eos_token_id,
    tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

text_streamer = TextStreamer(tokenizer)
_ = model.generate(
    input_ids,
    max_new_tokens=4096,
    eos_token_id=terminators,
    do_sample=True,
    streamer = text_streamer,
    temperature=0.6,
    top_p=0.9,
    repetition_penalty = 1.1
)

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: Dongwookss
Model type: text generation
Language(s) (NLP): Korean
Finetuned from model : HuggingFaceH4/zephyr-7b-beta

Data

https://huggingface.co/datasets/Dongwookss/q_a_korean_futsal

학습 데이터셋은 nlpai-lab/databricks-dolly-15k-ko 를 베이스로 추가, 구축, 전처리 진행한 2.33k 데이터로 튜닝하였습니다. 데이터셋은 instruction, input, output 으로 구성되어 있으며 tuning 목표에 맞게 말투 수정하였습니다. 도메인 정보에 대한 데이터 추가하였습니다.

Training & Result

Training Procedure

LoRA와 SFT Trainer 방식을 사용하였습니다.

Training Hyperparameters

Training regime: bf16 mixed precision

  r=32,
  lora_alpha=64,  #  QLoRA : alpha = r/2 // LoRA : alpha =r*2
  lora_dropout=0.05, 
  target_modules=[
  "q_proj",
  "k_proj",
  "v_proj",
  "o_proj",
  "gate_proj",
  "up_proj",
  "down_proj",
  ],  # 타겟 모듈

Result

https://github.com/lucide99/Chatbot_FutFut

Environment

L4 GPU

Downloads last month: 3

Safetensors

Model size

7B params

Tensor type

BF16

mintaeng
/

small_fut_final