Quantization made by Richard Erkhov.

SJ-SOLAR-10.7b-DPO - GGUF

Model creator: https://huggingface.co/SJ-Donald/
Original model: https://huggingface.co/SJ-Donald/SJ-SOLAR-10.7b-DPO/

Name	Quant method	Size
SJ-SOLAR-10.7b-DPO.Q2_K.gguf	Q2_K	3.8GB
SJ-SOLAR-10.7b-DPO.IQ3_XS.gguf	IQ3_XS	4.22GB
SJ-SOLAR-10.7b-DPO.IQ3_S.gguf	IQ3_S	4.45GB
SJ-SOLAR-10.7b-DPO.Q3_K_S.gguf	Q3_K_S	4.42GB
SJ-SOLAR-10.7b-DPO.IQ3_M.gguf	IQ3_M	4.59GB
SJ-SOLAR-10.7b-DPO.Q3_K.gguf	Q3_K	4.92GB
SJ-SOLAR-10.7b-DPO.Q3_K_M.gguf	Q3_K_M	4.92GB
SJ-SOLAR-10.7b-DPO.Q3_K_L.gguf	Q3_K_L	5.34GB
SJ-SOLAR-10.7b-DPO.IQ4_XS.gguf	IQ4_XS	5.51GB
SJ-SOLAR-10.7b-DPO.Q4_0.gguf	Q4_0	5.74GB
SJ-SOLAR-10.7b-DPO.IQ4_NL.gguf	IQ4_NL	5.8GB
SJ-SOLAR-10.7b-DPO.Q4_K_S.gguf	Q4_K_S	5.78GB
SJ-SOLAR-10.7b-DPO.Q4_K.gguf	Q4_K	6.1GB
SJ-SOLAR-10.7b-DPO.Q4_K_M.gguf	Q4_K_M	6.1GB
SJ-SOLAR-10.7b-DPO.Q4_1.gguf	Q4_1	6.36GB
SJ-SOLAR-10.7b-DPO.Q5_0.gguf	Q5_0	6.98GB
SJ-SOLAR-10.7b-DPO.Q5_K_S.gguf	Q5_K_S	6.98GB
SJ-SOLAR-10.7b-DPO.Q5_K.gguf	Q5_K	7.17GB
SJ-SOLAR-10.7b-DPO.Q5_K_M.gguf	Q5_K_M	7.17GB
SJ-SOLAR-10.7b-DPO.Q5_1.gguf	Q5_1	7.6GB
SJ-SOLAR-10.7b-DPO.Q6_K.gguf	Q6_K	8.3GB
SJ-SOLAR-10.7b-DPO.Q8_0.gguf	Q8_0	10.75GB

Original model description:

license: cc-by-nc-4.0 tags: - DPO model-index: - name: SJ-SOLAR-10.7b-DPO 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: 68.26 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SJ-Donald/SJ-SOLAR-10.7b-DPO 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: 86.95 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SJ-Donald/SJ-SOLAR-10.7b-DPO 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: 66.73 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SJ-Donald/SJ-SOLAR-10.7b-DPO 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: 67.74 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SJ-Donald/SJ-SOLAR-10.7b-DPO 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: 84.21 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SJ-Donald/SJ-SOLAR-10.7b-DPO 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: 62.09 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SJ-Donald/SJ-SOLAR-10.7b-DPO name: Open LLM Leaderboard

SJ-Donald/SJ-SOLAR-10.7b-DPO

SJ-Donald/SJ-SOLAR-10.7b-DPO is fine-tuned using DPO method.

Environment

Using Google CoLab A100

Base model

SJ-Donald/SOLAR-10.7B-slerp

Datasets

SJ-Donald/orca-dpo-pairs-ko

Benchmark

Open-LLM-Leaderboard(https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)

Average	ARC	HellaSwag	MMLU	TruthfulQA	Winogrande	GSM8K
72.67	68.26	86.95	66.73	67.74	84.21	62.03

open-ko-llm-leaderboard(https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)

Average	Ko-ARC	Ko-HellaSwag	Ko-MMLU	Ko-TruthfulQA	Ko-CommonGen V2
56.93	53.67	61.99	53.36	57.2	58.44

How to use

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = 'SJ-Donald/SJ-SOLAR-10.7b-DPO'

tokenizer = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
    repo,
    return_dict=True,
    torch_dtype=torch.float16,
    device_map='auto'
)

Chat Template

template = """### System:
{{system_content}}

### User:
{{question}}

### Assistant:
"""

GGUF Version

You can use gguf model file here! -> SJ-Donald/SJ-SOLAR-10.7b-DPO-GGUF

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	72.67
AI2 Reasoning Challenge (25-Shot)	68.26
HellaSwag (10-Shot)	86.95
MMLU (5-Shot)	66.73
TruthfulQA (0-shot)	67.74
Winogrande (5-shot)	84.21
GSM8k (5-shot)	62.09