-
Hi,
I'm trying to apply context-debias to generative models (gpt2). I tried to directly use your script but the loss is extremely large (1e10+). I notice you have an argument "mlm" in run_debias_mlm…
-
Hi, i have just used the default params to p-tune the gpt2-medium on LAMA task and the results is as follows.
best dev_hit@1: 51.8 best test_hit@1: 44.5
For the results I got, I have some confusions…
-
### Is your feature request related to a problem? / 你想要的功能和什么问题相关？
gpt2-chatbot
### Describe the solution you'd like. / 你想要的解决方案是什么？
gpt2-chatbot
### Describe alternatives you've considered. / 你考虑…
-
I try to run the GPT2 training script. The version is 2.2.0. But there is no "lightseq.training.ops.pytorch.quantization" file. In which version, can I run the GPT2 training example?
-
I want to fine-tune the model and do some machine translation based on Gpt-2. I created my dataset according to the Gpt-2 paper in this format: 'sentence1 = translation1 \n sentence2 = translation2 \n…
-
I get this error when trying to convert `gpt2`
```
/site-packages/coremltools/converters/mil/mil/input_type.py", line 162, in validate_inputs
raise ValueError(msg.format(name, var.name, input…
-
Thanks for the great work - I was wondering if you could upload the pretrained GPT2 model checkpoints (e.g. GPT2 Small & Medium C2S, NL+C2S) somewhere?
I am planning to use your work on several ot…
-
When I run **"demo.ipynb"**, I replace the model with GPT2, but when the code runs to "if filter_cand: cands = cands + [cands[-1]] * (len(control_cand) - len(cands))", an error occurs: **list index ou…
-
If I run the training command for Slake dataset with "python main.py", I got the following error:
```
File "main.py", line 86, in
model = pytorch_model_run(train_dataloader, val_dataloader, …
-
# 1. AttributeError: 'Namespace' object has no attribute 'deepspeed_config_dict'. Did you mean: 'deepspeed_config'?
```
export MAX_JOBS=8
export NCCL_DEBUG=error
export NCCL_SOCKET_IFNAME=ens8
…