You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

Model Card for Model TwinDoc/RedWhale-2-12B

Llama3.1 8B๋ฅผ TLIํ•˜์—ฌ 12B ๋ชจ๋ธ๋กœ ๋งŒ๋“  ํ›„ ์‚ฌ์ „ํ•™์Šตํ•œ ๋ชจ๋ธ์ž…๋‹ˆ๋‹ค. ์‚ฌ์ „ํ•™์Šต์€ ํ•œ๊ตญ์–ด Corpus๋กœ ์ง„ํ–‰ํ•˜์˜€์Šต๋‹ˆ๋‹ค.
TLI๋Š” transformer์˜ layer๋ฅผ ๋ณต์ œํ•˜๋Š” ๋ชจ๋ธ up-scale ๋ฐฉ๋ฒ•๋ก ์ž…๋‹ˆ๋‹ค.

Model Details

Model Description

  • Developed by: AgileSoda
  • Model type: Llama
  • Language(s) (NLP): ํ•œ๊ตญ์–ด
  • License: [More Information Needed]
  • Finetuned from model [optional]: TwinDoc/RedWhale-2-12B-Instruct
  • Foundation Model: RedWhale-2-12B-TLI

Model Sources [optional]

  • Repository: [More Information Needed]
  • Paper [optional]: [More Information Needed]
  • Demo [optional]: [More Information Needed]

Uses

RedWhale-2-12B ๋ชจ๋ธ ์‚ฌ์šฉ ๋ฐฉ๋ฒ•์€ meta-llama/Llama-3.1-8B ๋ชจ๋ธ ์‚ฌ์šฉ ๋ฐฉ๋ฒ•๊ณผ ๋™์ผํ•ฉ๋‹ˆ๋‹ค. ์‚ฌ์šฉํ•˜๊ณ ์ž ํ•˜๋Š” ์„œ๋น™ ์—”์ง„์˜ ๊ณต์‹ ๋ฌธ์„œ๋ฅผ ์ฐธ๊ณ ํ•˜์„ธ์š”. ๋‹ค์Œ์€ ์˜ˆ์‹œ์ž…๋‹ˆ๋‹ค.

Direct Use

usage with Transformers ์˜ˆ์‹œ ์ฝ”๋“œ๋Š” transformers == 4.48.1์—์„œ ์ž‘์„ฑ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.

from transformers import AutoModelForCausalLM,AutoTokenizer
import torch

loading_args = {"torch_dtype": torch.bfloat16, "device_map": "auto"} ## for multi gpu loading
model = AutoModelForCausalLM.from_pretrained("TwinDoc/RedWhale-2-12B",**loading_args)
tokenizer = AutoTokenizer.from_pretrained("TwinDoc/RedWhale-2-12B")

text = "๋Œ€ํ•œ๋ฏผ๊ตญ์˜ ์ˆ˜๋„๋Š” "
inputs = tokenizer(text,return_tensors="pt")
outputs = model.generate(**inputs,max_new_tokens = 100)
>>> print(tokenizer.decode(outputs[0]))
"<|begin_of_text|>๋Œ€ํ•œ๋ฏผ๊ตญ์˜ ์ˆ˜๋„๋Š” 1000๋งŒ์—ฌ ๋ช… ์ด์ƒ์ด ๊ฑฐ์ฃผํ•˜๊ณ  ์žˆ๋Š” ์„œ์šธ๋กœ ๋Œ€ํ‘œ๋˜๋Š” ๋„์‹ฌ์ง€์ด๋‹ค. ๋ณธ ์—ฐ๊ตฌ์—์„œ๋Š” ์„œ์šธ์˜ ์ค‘์‹ฌ์„ ๋‚˜ํƒ€๋‚ด๋Š” 4๋Œ€๋ฌธ ์•ˆ์„ ๋„์‹ฌ์ง€๋กœ ์ •์˜ํ•˜๊ณ , ๊ทธ ๊ฒฝ๊ณ„๋ฅผ ๋ถ์•…์‚ฐ, ์ธ์™•์‚ฐ, ๋‚จ์‚ฐ, ๋‚™์‚ฐ์œผ๋กœ ๊ตฌ๋ถ„ํ•˜๋Š” 4์‚ฐ์˜ ์‚ฐ์ค„๊ธฐ์™€ ๋„๋กœ๋กœ ๊ตฌ์„ฑ๋˜๋Š” 8๊ฐœ์˜ ๋ณ€์„ ๊ฒฝ๊ณ„๋กœ ์ •ํ•œ๋‹ค. ๊ตญํ†  ๊ณต๊ฐ„์  ๊ด€์ ์—์„œ ์šฐ๋ฆฌ๋‚˜๋ผ์˜"

Out-of-Scope Use

์‚ฌ์ „ํ•™์Šต๋งŒ ์ง„ํ–‰ํ•œ ๋ชจ๋ธ์ด๊ธฐ ๋•Œ๋ฌธ์— Instruction์„ ๋”ฐ๋ฅด๋Š” ๋Šฅ๋ ฅ์€ ์—†์Šต๋‹ˆ๋‹ค. ํŠน์ • Task์— ๋ฐ”๋กœ ์‚ฌ์šฉํ•˜๊ธฐ ๋ณด๋‹ค๋Š” Fine-Tuning์„ ์œ„ํ•œ Base๋ชจ๋ธ๋กœ ์‚ฌ์šฉํ•˜๋Š” ๊ฒƒ์„ ๊ถŒ์žฅํ•ฉ๋‹ˆ๋‹ค.

Training Details

Training Data

Training Procedure

Compute Infrastructure

Hardware

  • L40 48GB * 4EA
Downloads last month
2
Safetensors
Model size
11.5B params
Tensor type
F32
ยท
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Collection including TwinDoc/RedWhale-2-12B