Wang Chenguang

if I want to train this model without char,what should i do?

5

hello : if i want to train this model without char,what should i do? I want to make a comparison between the model with a char and the model with...

When I use the model to make a prediction，i also let the use_character_lstm = False，it is have some wrong， Traceback (most recent call last): File "/home/wcg/tools/local/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1327, in _do_call...

when i make the [ann] ：use_character_lstm = False，Some problems have arisen.

1

tensorboard_character_embeddings.tensor_name = model.character_embedding_weights.name AttributeError: 'EntityLSTM' object has no attribute 'character_embedding_weights' 

模型推理报错，请教问题，ValueError: (InvalidArgument) Deserialize to tensor failed

2

### 模型推理报错，请教出现错误原因 我用paddle版本，paddlepaddle-gpu 2.6.1 通过torch2paddle，转换得到模型文件目录： ├── inference_model │   ├── model.pdiparams │   ├── model.pdiparams.info │   └── model.pdmodel ├── layer_model │   ├── `__ model__ -> ../inference_model/model.pdmodel` │   ├── `__params__ -> ../inference_model/model.pdiparams` │  ...

Paddle-Inference-Demo，这行代码错了吧

1

https://github.com/PaddlePaddle/Paddle-Inference-Demo/blob/cbf3a528eedf876d2b59409c406ef64aee29772f/python/advanced/multi_thread/threads_demo.py#L104 是不是应该是： for t in threads： t.join()

AttributeError： 'DeepSpeedEngine' object has no attribute 'model'，

1

https://github.com/microsoft/DeepSpeedExamples/blob/957ae3141946daf9a6bc5731e261032a13a82f05/applications/DeepSpeed-Chat/training/step1_supervised_finetuning/main.py#L367 just train one epoch，i got this error ，how to solve the problem ？ ***** Running training ***** ***** Evaluating perplexity, Epoch 0/16 ***** Using `past_key_values` as a tuple is...

[BUG] error ：past_key, past_value = layer_past，how to solve this ?

2

**Describe the bug** when i run train，rlhf step 3； ``` Actor_Lr=9.65e-6 Critic_Lr=5e-6 #--data_path Dahoas/rm-static \ #--offload_reference_model \ deepspeed --master_port 12346 main_step3.py \ --data_path ${data_path}/beyond/rlhf-reward-single-round-trans_chinese_step3 \ --data_split 2,4,4 \ --actor_model_name_or_path $ACTOR_MODEL_PATH...