LoneStriker/Yi-6B-Spicyboros-3.1-3.0bpw-h6-exl2

Yi

LoneStriker fine-tune of Yi using Spicyboros-3.1 dataset

Introduction

The Yi series models are large language models trained from scratch by developers at 01.AI. The first public release contains two base models with the parameter size of 6B and 34B.

News

• 🎯 2023/11/02: The base model of Yi-6B and Yi-34B

Model Performance

Model	MMLU	CMMLU	C-Eval	GAOKAO	BBH	Commonsense Reasoning	Reading Comprehension	Math & Code
	5-shot	5-shot	5-shot	0-shot	3-shot@1	-	-	-
LLaMA2-34B	62.6	-	-	-	44.1	69.9	68.0	26.0
LLaMA2-70B	68.9	53.3	-	49.8	51.2	71.9	69.4	36.8
Baichuan2-13B	59.2	62.0	58.1	54.3	48.8	64.3	62.4	23.0
Qwen-14B	66.3	71.0	72.1	62.5	53.4	73.3	72.5	39.8
Skywork-13B	62.1	61.8	60.6	68.1	41.7	72.4	61.4	24.9
InternLM-20B	62.1	59.0	58.8	45.5	52.5	78.3	-	26.0
Aquila-34B	67.8	71.4	63.1	-	-	-	-	-
Falcon-180B	70.4	58.0	57.8	59.0	54.0	77.3	68.8	34.0
Yi-6B	63.2	75.5	72.0	72.2	42.8	72.3	68.7	19.8
Yi-34B	76.3	83.7	81.4	82.8	54.3	80.1	76.4	37.1

While benchmarking open-source models, we have observed a disparity between the results generated by our pipeline and those reported in public sources (e.g. OpenCampus). Upon conducting a more in-depth investigation of this difference, we have discovered that various models may employ different prompts, post-processing strategies, and sampling techniques, potentially resulting in significant variations in the outcomes. Our prompt and post-processing strategy remains consistent with the original benchmark, and greedy decoding is employed during evaluation without any post-processing for the generated content. For scores that did not report by original author (including score reported with different setting), we try to get results with our pipeline.

To extensively evaluate model's capability, we adopted the methodology outlined in Llama2. Specifically, we included PIQA, SIQA, HellaSwag, WinoGrande, ARC, OBQA, and CSQA to assess common sense reasoning. SquAD, QuAC, and BoolQ were incorporated to evaluate reading comprehension. CSQA was exclusively tested using a 7-shot setup, while all other tests were conducted in a 0-shot configuration. Additionally, we introduced GSM8K (8-shot@1), MATH (4-shot@1), HumanEval (0-shot@1), and MBPP (3-shot@1) under the category "Math & Code". Due to technical constraints, we did not test Falcon-180 on QuAC and OBQA; the score is derived by averaging the scores on the remaining tasks. Since the scores for these two tasks are generally lower than the average, we believe that Falcon-180B's performance was not underestimated.

Disclaimer

Although we use data compliance checking algorithms during the training process to ensure the compliance of the trained model to the best of our ability, due to the complexity of the data and the diversity of language model usage scenarios, we cannot guarantee that the model will generate correct and reasonable output in all scenarios. Please be aware that there is still a risk of the model producing problematic outputs. We will not be responsible for any risks and issues resulting from misuse, misguidance, illegal usage, and related misinformation, as well as any associated data security concerns.

License

The Yi series model must be adhere to the Model License Agreement. For any questions related to licensing and copyright, please contact us ([email protected]).