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 8Bλ₯Ό TLIν•˜μ—¬ 12B λͺ¨λΈλ‘œ λ§Œλ“  ν›„ μ‚¬μ „ν•™μŠ΅ν•œ λͺ¨λΈμž…λ‹ˆλ‹€. μ‚¬μ „ν•™μŠ΅μ€ ν•œκ΅­μ–΄ Corpus둜 μ§„ν–‰ν•˜μ˜€μŠ΅λ‹ˆλ‹€.
TLIλŠ” transformer의 layerλ₯Ό λ³΅μ œν•˜λŠ” λͺ¨λΈ up-scale λ°©λ²•λ‘ μž…λ‹ˆλ‹€.

Model Details

Model Description

  • Developed by: AgileSoda
  • Model type: Llama
  • Language(s) (NLP): ν•œκ΅­μ–΄
  • 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 λͺ¨λΈ μ‚¬μš© 방법은 meta-llama/Llama-3.1-8B λͺ¨λΈ μ‚¬μš© 방법과 λ™μΌν•©λ‹ˆλ‹€. μ‚¬μš©ν•˜κ³ μž ν•˜λŠ” μ„œλΉ™ μ—”μ§„μ˜ 곡식 λ¬Έμ„œλ₯Ό μ°Έκ³ ν•˜μ„Έμš”. λ‹€μŒμ€ μ˜ˆμ‹œμž…λ‹ˆλ‹€.

Direct Use

usage with Transformers μ˜ˆμ‹œ μ½”λ“œλŠ” transformers == 4.48.1μ—μ„œ μž‘μ„±λ˜μ—ˆμŠ΅λ‹ˆλ‹€.

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 = "λŒ€ν•œλ―Όκ΅­μ˜ μˆ˜λ„λŠ” "
inputs = tokenizer(text,return_tensors="pt")
outputs = model.generate(**inputs,max_new_tokens = 100)
>>> print(tokenizer.decode(outputs[0]))
"<|begin_of_text|>λŒ€ν•œλ―Όκ΅­μ˜ μˆ˜λ„λŠ” 1000λ§Œμ—¬ λͺ… 이상이 κ±°μ£Όν•˜κ³  μžˆλŠ” μ„œμšΈλ‘œ λŒ€ν‘œλ˜λŠ” 도심지이닀. λ³Έ μ—°κ΅¬μ—μ„œλŠ” μ„œμšΈμ˜ 쀑심을 λ‚˜νƒ€λ‚΄λŠ” 4λŒ€λ¬Έ μ•ˆμ„ λ„μ‹¬μ§€λ‘œ μ •μ˜ν•˜κ³ , κ·Έ 경계λ₯Ό 뢁악산, 인왕산, 남산, λ‚™μ‚°μœΌλ‘œ κ΅¬λΆ„ν•˜λŠ” 4μ‚°μ˜ 산쀄기와 λ„λ‘œλ‘œ κ΅¬μ„±λ˜λŠ” 8개의 변을 κ²½κ³„λ‘œ μ •ν•œλ‹€. κ΅­ν†  곡간적 κ΄€μ μ—μ„œ μš°λ¦¬λ‚˜λΌμ˜"

Out-of-Scope Use

μ‚¬μ „ν•™μŠ΅λ§Œ μ§„ν–‰ν•œ λͺ¨λΈμ΄κΈ° λ•Œλ¬Έμ— Instruction을 λ”°λ₯΄λŠ” λŠ₯λ ₯은 μ—†μŠ΅λ‹ˆλ‹€. νŠΉμ • Task에 λ°”λ‘œ μ‚¬μš©ν•˜κΈ° λ³΄λ‹€λŠ” Fine-Tuning을 μœ„ν•œ Baseλͺ¨λΈλ‘œ μ‚¬μš©ν•˜λŠ” 것을 ꢌμž₯ν•©λ‹ˆλ‹€.

Training Details

Training Data

Training Procedure

Compute Infrastructure

Hardware

  • L40 48GB * 4EA
Downloads last month
0
Safetensors
Model size
11.5B params
Tensor type
F32
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Collection including TwinDoc/RedWhale-2-12B