Downloads · 30 days
23
2% of all-time downloads
RichardErkhov/jingyeom_-_SOLAR_KO_1.3_deup-gguf
jingyeom_-_SOLAR_KO_1.3_deup-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
23
2% of all-time downloads
All-time downloads
1.1K
Public
Repo size
123 GB
Likes
0
Public
Click a slice to open those files.
.gguf143 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
SOLAR_KO_1.3_deup - GGUF
| Name | Quant method | Size |
|---|---|---|
| SOLAR_KO_1.3_deup.Q2_K.gguf | Q2_K | 3.79GB |
| SOLAR_KO_1.3_deup.IQ3_XS.gguf | IQ3_XS | 4.21GB |
| SOLAR_KO_1.3_deup.IQ3_S.gguf | IQ3_S | 4.44GB |
| SOLAR_KO_1.3_deup.Q3_K_S.gguf | Q3_K_S | 4.41GB |
| SOLAR_KO_1.3_deup.IQ3_M.gguf | IQ3_M | 4.58GB |
| SOLAR_KO_1.3_deup.Q3_K.gguf | Q3_K | 4.91GB |
| SOLAR_KO_1.3_deup.Q3_K_M.gguf | Q3_K_M | 4.91GB |
| SOLAR_KO_1.3_deup.Q3_K_L.gguf | Q3_K_L | 5.33GB |
| SOLAR_KO_1.3_deup.IQ4_XS.gguf | IQ4_XS | 5.5GB |
| SOLAR_KO_1.3_deup.Q4_0.gguf | Q4_0 | 5.73GB |
| SOLAR_KO_1.3_deup.IQ4_NL.gguf | IQ4_NL | 5.8GB |
| SOLAR_KO_1.3_deup.Q4_K_S.gguf | Q4_K_S | 5.78GB |
| SOLAR_KO_1.3_deup.Q4_K.gguf | Q4_K | 6.1GB |
| SOLAR_KO_1.3_deup.Q4_K_M.gguf | Q4_K_M | 6.1GB |
| SOLAR_KO_1.3_deup.Q4_1.gguf | Q4_1 | 6.35GB |
| SOLAR_KO_1.3_deup.Q5_0.gguf | Q5_0 | 6.97GB |
| SOLAR_KO_1.3_deup.Q5_K_S.gguf | Q5_K_S | 6.97GB |
| SOLAR_KO_1.3_deup.Q5_K.gguf | Q5_K | 7.16GB |
| SOLAR_KO_1.3_deup.Q5_K_M.gguf | Q5_K_M | 7.16GB |
| SOLAR_KO_1.3_deup.Q5_1.gguf | Q5_1 | 7.59GB |
| SOLAR_KO_1.3_deup.Q6_K.gguf | Q6_K | 8.29GB |
| SOLAR_KO_1.3_deup.Q8_0.gguf | Q8_0 | 10.74GB |
base_model : beomi/OPEN-SOLAR-KO-10.7B
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_name = "jingyeom/SOLAR_KO_1.3_deup"
model = AutoModelForCausalLM.from_pretrained(
model_name,
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
Ko-LLM-Leaderboard (24.01.29 기준 리더보드 11등)
| Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
|---|---|---|---|---|---|
| 53.63 | 52.65 | 60.92 | 50.9 | 45.14 | 58.56 |