squarelike_-_llama-2-koen-story-13b-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
squarelike_-_llama-2-koen-story-13b-gguf

like

0

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

llama-2-koen-story-13b - GGUF

Model creator: https://huggingface.co/squarelike/
Original model: https://huggingface.co/squarelike/llama-2-koen-story-13b/

Name	Quant method	Size
llama-2-koen-story-13b.Q2_K.gguf	Q2_K	4.6GB
llama-2-koen-story-13b.Q3_K_S.gguf	Q3_K_S	5.36GB
llama-2-koen-story-13b.Q3_K.gguf	Q3_K	5.99GB
llama-2-koen-story-13b.Q3_K_M.gguf	Q3_K_M	5.99GB
llama-2-koen-story-13b.Q3_K_L.gguf	Q3_K_L	6.54GB
llama-2-koen-story-13b.IQ4_XS.gguf	IQ4_XS	6.63GB
llama-2-koen-story-13b.Q4_0.gguf	Q4_0	6.95GB
llama-2-koen-story-13b.IQ4_NL.gguf	IQ4_NL	6.49GB
llama-2-koen-story-13b.Q4_K_S.gguf	Q4_K_S	7.01GB
llama-2-koen-story-13b.Q4_K.gguf	Q4_K	2.77GB
llama-2-koen-story-13b.Q4_K_M.gguf	Q4_K_M	4.13GB
llama-2-koen-story-13b.Q4_1.gguf	Q4_1	7.71GB
llama-2-koen-story-13b.Q5_0.gguf	Q5_0	5.79GB
llama-2-koen-story-13b.Q5_K_S.gguf	Q5_K_S	3.59GB
llama-2-koen-story-13b.Q5_K.gguf	Q5_K	2.03GB
llama-2-koen-story-13b.Q5_K_M.gguf	Q5_K_M	5.49GB
llama-2-koen-story-13b.Q5_1.gguf	Q5_1	9.21GB
llama-2-koen-story-13b.Q6_K.gguf	Q6_K	10.06GB
llama-2-koen-story-13b.Q8_0.gguf	Q8_0	13.03GB

Original model description:

language:

ko tags:
pytorch
causal-lm license: llama2 pipeline_tag: text-generation

llama-2-ko-story-7b

llama-2-koen-story-13b는 beomi/llama-2-koen-13b를 기반으로 한글 소설 raw 데이터를 학습시킨 기반 모델입니다.

학습 데이터

llama-2-koen-story-13b는 약 167MB의 한글 소설 말뭉치로 학습되었습니다. 주요 데이터셋은 다음과 같습니다.

Source	Size (MB)	Link
한글 소설 말뭉치	115.0
공유마당 한국 고전 문학 말뭉치	53.0	https://gongu.copyright.or.kr/

학습

llama-2-koen-story-13b는 beomi/llama-2-koen-13b에서 qlora로 추가 학습되었습니다.

lora_alpha: 16
lora_dropout: 0.05
lora_r: 32
target_modules: q_proj, v_proj
epoch: 3
learning_rate: 3e-4