hgloow/Sakura-SOLAR-Instruct-EXL2

Sakura-SOLAR-Instruct

• Model creator: KyujinHan
• Original model: Merged AGI 7B
• Is a merge of:
  • VAGOsolutions/SauerkrautLM-SOLAR-Instruct
  • upstage/SOLAR-10.7B-Instruct-v1.0

Quantizations

Measured using ExLlamav2_HF and 4096 max_seq_len with Oobabooga's Text Generation WebUI.

I also provided zipped quantization because a lot of people find gguf single download convenient. Zipped quantization is relatively smaller in size to download. After extracted, you can use the model folder as usual.

Use TheBloke's 4bit-32g quants (7.4GB VRAM usage) if you have 8GB cards.

Branch	BPW	Folder Size	Zipped File Size	VRAM Usage	Description
3.0bpw/3.0bpw-zip	3.0BPW	4.01GB	3.72GB	5.1 GB	For >=6GB VRAM cards with idle VRAM atleast or below 500MB (headroom for other things)
5.0bpw (main)/5.0bpw-zip	5.0BPW	6.45GB	6.3GB	7.7 GB	For >=10GB VRAM cards
6.0bpw/6.0bpw-zip	6.0BPW	7.66GB	7.4GB	9.0 GB	For >=10GB VRAM cards with idle VRAM atleast or below 500MB (headroom for other things)
7.0bpw/7.0bpw-zip	7.0BPW	8.89GB	8.6GB	10.2 GB	For >=11GB VRAM cards with idle VRAM atleast or below 500MB (headroom for other things)
8.0bpw/8.0bpw-zip	8.0BPW	10.1GB	9.7GB	11.3 GB	For >=12GB VRAM cards with idle VRAM atleast or below 500MB (headroom for other things)

Calibration Dataset

• argilla/distilabel-math-preference-dpo
  • Training dataset of VAGOsolutions/SauerkrautLM-SOLAR-Instruct

Prompt template: Orca-Hashes

From TheBloke

### System:
{system_message}

### User:
{prompt}

### Assistant:

If you use Oobabooga's Chat tab

From my testing, the template "Orca-Mini" or any of the Orca templates produced the best result. Feel free to leave a suggestion if you know better.

Original Info

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

### 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)

---