-
# 🚀 Feature request
In Fairseq it is possible to forego setting a constant batch-size in favor of a dynamic batch size with --max_tokens. This ensures that a batch always consists of at max N=max_t…
-
Can we try to train different models like gpt2 or t5/mt5 in the bertin pipeline? gpt2 is more of a priority.
-
Hi,
Would the pytorch model file located in the multilingual folder work for applying the algorithm on french ?
Thank you.
ghost updated
2 years ago
-
## Environment info
- `transformers` version: 4.11.2
- Platform: google colab
- Python version: 3.7.12
- PyTorch version (GPU?):
- Tensorflow version (GPU?): 2.6.0
- Using GPU in script?: Ye…
-
## Environment info
- `transformers` version: 4.15.0.dev0
- Platform: Linux-5.10.68+-x86_64-with-debian-bullseye-sid
- Python version: 3.7.12
- PyTorch version (GPU?): 1.9.1 (True)
- Tensorfl…
-
## Environment info
- `transformers` version: 4.13
- Platform: linux
- Python version: 1.80
- PyTorch version (GPU?): gpu
@patil-suraj
Model :mt5-base
input : python run_summarizatio…
-
Based on [SO post](https://stackoverflow.com/q/70697470/17840900).
Goal: Amend [Bert-GLUE_OnnxRuntime_quantization.ipynb][1] to work with **Albert** and **Distilbert** models
Kernel: `conda_pyto…
-
## Reader Models Baseline
### **Extractive Models**
- `__ init __.py`
- `modeling_bart.py`
- `modeling_bert.py`
##### ※ Base : `AutoModelForQuestionAnswering`
### **Generative Mode…
-
## Environment info
- `transformers` version: latest (4.10.0.dev0)
- Python version: 3.8
- PyTorch version (GPU?): 1.9.0
- Using GPU in script?: no
- Using distributed or parallel set-up in s…
-
你好，非常感谢封神榜之前在 #111 和 #123 提供的帮助，我们现在已经成功完成一个对Wenzhong2.0-GPT2-3.5B-chinese模型的领域微调，但是微调后模型生成的是乱码。
我注意到 #89 也遇到了类似的问题，但似乎最后并没有解决，可否再麻烦大佬帮忙看一下。