You can deploy this model and start earning money today!

RichardErkhov/
jingyeom_-_freeze_KoSoLAR-10.7B-v0.2_1.4_dedup-gguf

Name: jingyeom_-_freeze_KoSoLAR-10.7B-v0.2_1.4_dedup-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

freeze_KoSoLAR-10.7B-v0.2_1.4_dedup - GGUF

Model creator: https://huggingface.co/jingyeom/
Original model: https://huggingface.co/jingyeom/freeze_KoSoLAR-10.7B-v0.2_1.4_dedup/

Name	Quant method	Size
freeze_KoSoLAR-10.7B-v0.2_1.4_dedup.Q2_K.gguf	Q2_K	3.77GB
freeze_KoSoLAR-10.7B-v0.2_1.4_dedup.IQ3_XS.gguf	IQ3_XS	4.18GB
freeze_KoSoLAR-10.7B-v0.2_1.4_dedup.IQ3_S.gguf	IQ3_S	4.41GB
freeze_KoSoLAR-10.7B-v0.2_1.4_dedup.Q3_K_S.gguf	Q3_K_S	4.39GB
freeze_KoSoLAR-10.7B-v0.2_1.4_dedup.IQ3_M.gguf	IQ3_M	4.56GB
freeze_KoSoLAR-10.7B-v0.2_1.4_dedup.Q3_K.gguf	Q3_K	4.88GB
freeze_KoSoLAR-10.7B-v0.2_1.4_dedup.Q3_K_M.gguf	Q3_K_M	4.88GB
freeze_KoSoLAR-10.7B-v0.2_1.4_dedup.Q3_K_L.gguf	Q3_K_L	5.31GB
freeze_KoSoLAR-10.7B-v0.2_1.4_dedup.IQ4_XS.gguf	IQ4_XS	5.47GB
freeze_KoSoLAR-10.7B-v0.2_1.4_dedup.Q4_0.gguf	Q4_0	5.7GB
freeze_KoSoLAR-10.7B-v0.2_1.4_dedup.IQ4_NL.gguf	IQ4_NL	5.77GB
freeze_KoSoLAR-10.7B-v0.2_1.4_dedup.Q4_K_S.gguf	Q4_K_S	5.75GB
freeze_KoSoLAR-10.7B-v0.2_1.4_dedup.Q4_K.gguf	Q4_K	6.07GB
freeze_KoSoLAR-10.7B-v0.2_1.4_dedup.Q4_K_M.gguf	Q4_K_M	6.07GB
freeze_KoSoLAR-10.7B-v0.2_1.4_dedup.Q4_1.gguf	Q4_1	6.32GB
freeze_KoSoLAR-10.7B-v0.2_1.4_dedup.Q5_0.gguf	Q5_0	6.94GB
freeze_KoSoLAR-10.7B-v0.2_1.4_dedup.Q5_K_S.gguf	Q5_K_S	6.94GB
freeze_KoSoLAR-10.7B-v0.2_1.4_dedup.Q5_K.gguf	Q5_K	7.13GB
freeze_KoSoLAR-10.7B-v0.2_1.4_dedup.Q5_K_M.gguf	Q5_K_M	7.13GB
freeze_KoSoLAR-10.7B-v0.2_1.4_dedup.Q5_1.gguf	Q5_1	7.56GB
freeze_KoSoLAR-10.7B-v0.2_1.4_dedup.Q6_K.gguf	Q6_K	8.26GB
freeze_KoSoLAR-10.7B-v0.2_1.4_dedup.Q8_0.gguf	Q8_0	10.69GB

Original model description:

license: apache-2.0

Model

base_model : yanolja/KoSOLAR-10.7B-v0.2
training objective: freeze, instruction Tuning

Dataset

공개 데이터 수집

Deduplicating Training Data Makes Language Models Better 알고리즘 활용
instruction version 1.4

Code

python

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_name = "jjingyeom/freeze_KoSoLAR-10.7B-v0.2_1.4_dedup"
model = AutoModelForCausalLM.from_pretrained(
        model_name,
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

RichardErkhov/jingyeom_-_freeze_KoSoLAR-10.7B-v0.2_1.4_dedup-gguf