Lychee X

gpt2 can't be trained for QA ?

5

### System Info - `transformers` version: 4.26.0.dev0 - Platform: Linux-3.10.0-1160.81.1.el7.x86_64-x86_64-with-glibc2.17 - Python version: 3.9.15 - Huggingface_hub version: 0.11.1 - PyTorch version (GPU?): 1.13.1+cu116 (True) - Tensorflow version (GPU?): not installed...

must I have a openai key to run the project ?

3

hi,dear I see the "**openai**" in the requirements.txt , if I has no ID of openai ,could I run this project ?

[BUG]RuntimeError: Step 1 exited with non-zero status 1

13

**Describe the bug** A clear and concise description of what the bug is. **To Reproduce** Steps to reproduce the behavior: [the official doc ](https://github.com/microsoft/DeepSpeed/blob/master/blogs/deepspeed-chat/chinese/README.md#2-%E7%AE%80%E6%B4%81%E9%AB%98%E6%95%88%E4%B8%94%E7%BB%8F%E6%B5%8E%E7%9A%84-chatgpt-%E8%AE%AD%E7%BB%83%E4%B8%8E%E6%8E%A8%E7%90%86%E4%BD%93%E9%AA%8C) `python train.py --actor-model facebook/opt-1.3b --reward-model facebook/opt-350m...

[BUG]error: can't copy 'deepspeed/accelerator': doesn't exist or not a regular file

9

**Describe the bug** A clear and concise description of what the bug is. **To Reproduce** Steps to reproduce the behavior: [the official doc](https://github.com/microsoft/DeepSpeed/blob/master/blogs/deepspeed-chat/chinese/README.md#2-%E7%AE%80%E6%B4%81%E9%AB%98%E6%95%88%E4%B8%94%E7%BB%8F%E6%B5%8E%E7%9A%84-chatgpt-%E8%AE%AD%E7%BB%83%E4%B8%8E%E6%8E%A8%E7%90%86%E4%BD%93%E9%AA%8C) ``` git clone https://github.com/microsoft/DeepSpeed.git cd DeepSpeed pip...

how to install the repo ?

4

hi,dear as the title ,could I install it with pip ? such as `pip install git+https://github.com/IDEA-Research/GroundingDINO`

no "--deepspeed" in step2 shell

1

can't find the "--deepspeed" in [main.py](https://github.com/microsoft/DeepSpeedExamples/blob/master/applications/DeepSpeed-Chat/training/step2_reward_model_finetuning/main.py) but find in shell(training/step2_reward_model_finetuning/training_scripts/single_gpu/run_350m.sh) ``` deepspeed --num_gpus 1 main.py --model_name_or_path facebook/opt-350m \ --num_padding_at_beginning 1 --gradient_accumulation_steps 2 --zero_stage $ZERO_STAGE \ --only_optimize_lora \ --deepspeed --output_dir $OUTPUT...

where is the default model path ?

1

hi,dear `python chat.py --path ${PATH-to-your-actor-model}` if I want use opt-1.3b model, how ?

[REQUEST] how to RLHF-fine-tune custom data for deepspeedChat?

5

hi,dear any doc for the data dir and the model to load and infer ? down is Chinese 大佬，微调的数据存放在哪啊？能改成自己的数据么？ 另外：最后微调好的模型在哪啊？怎么加载和推理啊？

[BUG] step3 AssertionError: --{actor,critic}_gradient_checkpointing and --only_optimizer_lora cannot be enabled at the same time.

2

**Describe the bug** A clear and concise description of what the bug is. **To Reproduce** Steps to reproduce the behavior: 1. Command/Script to reproduce 2. What packages are required and...

[REQUEST]预训练模型有中文能力么？能增加中文预训练模型么？

1

hi,dear 大佬 我尝试了下opt-1.3b的训练过程，结果英语能力都不如意，都是I‘m sorry 不理解，你能解释下吗？ https://github.com/microsoft/DeepSpeed/issues/3331