You can deploy this model and start earning money today!

RichardErkhov/
kyujinpy_-_Sakura-SOLAR-Instruct-gguf

Name: kyujinpy_-_Sakura-SOLAR-Instruct-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Sakura-SOLAR-Instruct - GGUF

Model creator: https://huggingface.co/kyujinpy/
Original model: https://huggingface.co/kyujinpy/Sakura-SOLAR-Instruct/

Name	Quant method	Size
Sakura-SOLAR-Instruct.Q2_K.gguf	Q2_K	3.73GB
Sakura-SOLAR-Instruct.IQ3_XS.gguf	IQ3_XS	4.14GB
Sakura-SOLAR-Instruct.IQ3_S.gguf	IQ3_S	4.37GB
Sakura-SOLAR-Instruct.Q3_K_S.gguf	Q3_K_S	4.34GB
Sakura-SOLAR-Instruct.IQ3_M.gguf	IQ3_M	4.51GB
Sakura-SOLAR-Instruct.Q3_K.gguf	Q3_K	4.84GB
Sakura-SOLAR-Instruct.Q3_K_M.gguf	Q3_K_M	4.84GB
Sakura-SOLAR-Instruct.Q3_K_L.gguf	Q3_K_L	5.26GB
Sakura-SOLAR-Instruct.IQ4_XS.gguf	IQ4_XS	5.43GB
Sakura-SOLAR-Instruct.Q4_0.gguf	Q4_0	5.66GB
Sakura-SOLAR-Instruct.IQ4_NL.gguf	IQ4_NL	5.72GB
Sakura-SOLAR-Instruct.Q4_K_S.gguf	Q4_K_S	5.7GB
Sakura-SOLAR-Instruct.Q4_K.gguf	Q4_K	6.02GB
Sakura-SOLAR-Instruct.Q4_K_M.gguf	Q4_K_M	6.02GB
Sakura-SOLAR-Instruct.Q4_1.gguf	Q4_1	6.27GB
Sakura-SOLAR-Instruct.Q5_0.gguf	Q5_0	6.89GB
Sakura-SOLAR-Instruct.Q5_K_S.gguf	Q5_K_S	6.89GB
Sakura-SOLAR-Instruct.Q5_K.gguf	Q5_K	7.08GB
Sakura-SOLAR-Instruct.Q5_K_M.gguf	Q5_K_M	7.08GB
Sakura-SOLAR-Instruct.Q5_1.gguf	Q5_1	7.51GB
Sakura-SOLAR-Instruct.Q6_K.gguf	Q6_K	8.2GB
Sakura-SOLAR-Instruct.Q8_0.gguf	Q8_0	10.62GB

Original model description:

language:

en license: cc-by-nc-sa-4.0 tags:
merge pipeline_tag: text-generation model-index:
name: Sakura-SOLAR-Instruct results:
- task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics:
  - type: acc_norm value: 70.99 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLAR-Instruct name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics:
  - type: acc_norm value: 88.42 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLAR-Instruct name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics:
  - type: acc value: 66.33 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLAR-Instruct name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics:
  - type: mc2 value: 71.79 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLAR-Instruct name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics:
  - type: acc value: 83.66 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLAR-Instruct name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics:
  - type: acc value: 65.2 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/Sakura-SOLAR-Instruct name: Open LLM Leaderboard

Sakura-SOLAR-Instruct

(주)미디어그룹사람과숲과 (주)마커의 LLM 연구 컨소시엄에서 개발된 모델입니다

Model Details

Model Developers Kyujin Han (kyujinpy)

Method
Using Mergekit.
I shared the information about my model. (training and code)
Please see: ⭐Sakura-SOLAR.

Blog

Sakura-SOLAR 모델 제작 과정 및 후기.

Model Benchmark

Open leaderboard

Follow up as link.

Model	Average	ARC	HellaSwag	MMLU	TruthfulQA	Winogrande	GSM8K
Sakura-SOLRCA-Instruct-DPO	74.05	71.16	88.49	66.17	72.10	82.95	63.46
Sakura-SOLAR-Instruct-DPO-v2	74.14	70.90	88.41	66.48	71.86	83.43	63.76
kyujinpy/Sakura-SOLAR-Instruct	74.40	70.99	88.42	66.33	71.79	83.66	65.20

Rank1 2023.12.27 PM 11:50

Implementation Code

python

### KO-Platypus
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

repo = "kyujinpy/Sakura-SOLAR-Instruct"
OpenOrca = AutoModelForCausalLM.from_pretrained(
        repo,
        return_dict=True,
        torch_dtype=torch.float16,
        device_map='auto'
)
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	74.40
AI2 Reasoning Challenge (25-Shot)	70.99
HellaSwag (10-Shot)	88.42
MMLU (5-Shot)	66.33
TruthfulQA (0-shot)	71.79
Winogrande (5-shot)	83.66
GSM8k (5-shot)	65.20

RichardErkhov/kyujinpy_-_Sakura-SOLAR-Instruct-gguf