siqi00

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the siqi00/mistralultrafeedbackunhelpfulchatprompt0.71.050320 dataset. This model was trained using Discriminative Fine-tuning (DFT), as described in the paper Discriminative Finetuning of Generative Large Language Models without Reward Models and Preference Data. The code is available at PenGuln/DFT. The following hyperparameters were used during training: - learningrate: 2e-06 - trainbatchsize: 4 - evalbatchsize: 8 - seed: 42 - distributedtype: multi-GPU - numdevices: 4 - gradientaccumulationsteps: 8 - totaltrainbatchsize: 128 - totalevalbatchsize: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lrschedulertype: cosine - lrschedulerwarmupratio: 0.1 - numepochs: 2 - Transformers 4.45.2 - Pytorch 2.1.2+cu121 - Datasets 3.0.1 - Tokenizers 0.20.1

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the siqi00/mistralultrafeedbackunhelpfulchatprompt0.71.050320 dataset. It was finetuned as part of the paper Discriminative Finetuning of Generative Large Language Models without Reward Models and Preference Data The code is available at https://github.com/PenGuln/DFT. The following hyperparameters were used during training: - learningrate: 2e-06 - trainbatchsize: 4 - evalbatchsize: 8 - seed: 42 - distributedtype: multi-GPU - numdevices: 4 - gradientaccumulationsteps: 8 - totaltrainbatchsize: 128 - totalevalbatchsize: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lrschedulertype: cosine - lrschedulerwarmupratio: 0.1 - numepochs: 2 - Transformers 4.45.2 - Pytorch 2.1.2+cu121 - Datasets 3.0.1 - Tokenizers 0.20.1 The model can be used for text generation tasks. A basic example using the `transformers` library is shown below: Remember to install the necessary libraries (`pip install transformers`) and adjust parameters like `temperature` and `maxnewtokens` to fine-tune generation.