Yi 34B 200K
Created at 03.02.2024 14:05Assessment of the main tasks: 0.455
The table will scroll to the left
| Task name | Result | Metric |
|---|---|---|
| LCS | 0.108 | Accuracy |
| RCB | 0.498 / 0.402 | Avg. F1 / Accuracy |
| USE | 0.049 | Grade Norm |
| RWSD | 0.562 | Accuracy |
| PARus | 0.74 | Accuracy |
| ruTiE | 0.602 | Accuracy |
| MultiQ | 0.185 / 0.107 | F1-score/EM |
| CheGeKa | 0.01 / 0 | F1 / EM |
| ruModAr | 0.635 | EM |
| ruMultiAr | 0.277 | EM |
| MathLogicQA | 0.473 | Accuracy |
| ruWorldTree | 0.838 / 0.838 | Avg. F1 / Accuracy |
| ruOpenBookQA | 0.748 / 0.746 | Avg. F1 / Accuracy |
Evaluation on open tasks:
It is not taken into account in the overall ratingThe table will scroll to the left
| Task name | Result | Metric | ||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| BPS | 0.426 | Accuracy | ||||||||||||||||||||||||
| ruMMLU | 0.676 | Accuracy | ||||||||||||||||||||||||
| SimpleAr | 0.981 | EM | ||||||||||||||||||||||||
| ruHumanEval | 0.004 / 0.021 / 0.043 | pass@k | ||||||||||||||||||||||||
| ruHHH |
0.601
|
Accuracy | ||||||||||||||||||||||||
| ruHateSpeech |
0.626
|
Accuracy | ||||||||||||||||||||||||
| ruDetox |
|
Overall average score (J) Assessment of the preservation of meaning (SIM) Assessment of naturalness (FL) Style Transfer Accuracy (STA) |
||||||||||||||||||||||||
| ruEthics |
Table results:
[[-0.12, -0.113
, -0.108, -0.125
, -0.082], |
5 MCC |
Information about the submission:
Team:
LM Research
Name of the ML model:
Yi 34B 200K
Link to the ML model:
https://huggingface.co/01-ai/Yi-34B-200KAdditional links:
https://github.com/01-ai/YiArchitecture description:
The Yi 34B follow the same model architecture as LLaMA with a 200k context window size.
Description of the training:
Yi has independently created its own efficient training pipelines, and robust training infrastructure entirely from the ground up.
Pretrain data:
Trained on 3T multilingual corpus.
Training Details:
Yi has independently created its own high-quality training datasets, efficient training pipelines, and robust training infrastructure entirely from the ground up.
License:
Apache 2.0 license
Strategy, generation and parameters:
Code version v.1.1.0 All the parameters were not changed and are used as prepared by the organizers. Details: - 2 x NVIDIA A100 - dtype float16 - Pytorch 2.1.2 + CUDA 12.1 - Transformers 4.36.2 - Context length 11000
