Mixtral 8x7B Instruct
Created at 03.02.2024 13:28General assessment: 0.478
The table will scroll to the left
| Task name | Result | Metric |
|---|---|---|
| BPS | 0.157 | Accuracy |
| LCS | 0.082 | Accuracy |
| RCB | 0.521 / 0.48 | Avg. F1 / Accuracy |
| USE | 0.069 | Grade Norm |
| RWSD | 0.635 | Accuracy |
| PARus | 0.858 | Accuracy |
| ruTiE | 0.695 | Accuracy |
| MultiQ | 0.151 / 0.071 | F1-score/EM |
| ruMMLU | 0.776 | Accuracy |
| CheGeKa | 0.071 / 0 | F1 / EM |
| ruModAr | 0.674 | Accuracy |
| SimpleAr | 0.977 | Accuracy |
| ruMultiAr | 0.288 | Accuracy |
| MathLogicQA | 0.408 | Accuracy |
| ruHumanEval | 0.024 / 0.122 / 0.244 | pass@k |
| ruWorldTree | 0.907 / 0.907 | Avg. F1 / Accuracy |
| ruOpenBookQA | 0.825 / 0.825 | Avg. F1 / Accuracy |
Evaluation on diagnostic datasets:
It is not taken into account in the overall ratingThe table will scroll to the left
| Task name | Result | Metric | ||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ruHHH |
0.747
|
Accuracy | ||||||||||||||||||||||||
| ruHateSpeech |
0.785
|
Accuracy | ||||||||||||||||||||||||
| ruDetox |
|
Overall average score (J) Assessment of the preservation of meaning (SIM) Assessment of naturalness (FL) Style Transfer Accuracy (STA) |
||||||||||||||||||||||||
| ruEthics |
Table results:
[[-0.352, -0.409
, -0.387, -0.349
, -0.312], |
5 MCC |
Information about the submission:
Team:
Russian_NLP
Name of the ML model:
Mixtral 8x7B Instruct
Link to the ML model:
https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1Additional links:
https://mistral.ai/news/mixtral-of-experts/ https://huggingface.co/mistralai/Mixtral-8x7B-v0.1Architecture description:
Mixtral 8x7B Instruct is the instructed version of Mixtral 8x7B. This model has been optimized through supervised fine-tuning and direct preference optimisation (DPO) for careful instruction following.
Description of the training:
Mixtral is pre-trained on data extracted from the open Web – we train experts and routers simultaneously. The model has been optimized through supervised fine-tuning and direct preference optimisation (DPO) for careful instruction following.
Pretrain data:
The Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. The Mistral-8x7B outperforms Llama 2 70B on most benchmarks.
Training Details:
-
License:
Apache 2.0.
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 + accelerate - dtype bfloat16 - Pytorch 2.0.1 + CUDA 11.7 - Transformers 4.36.2 - Context length 10624
