stanford_alpaca icon indicating copy to clipboard operation
stanford_alpaca copied to clipboard

Code and documentation to train Stanford's Alpaca models, and generate the data.

Results 228 stanford_alpaca issues
Sort by recently updated
recently updated
newest added

## ImportError when using `weight_diff.py` script. ### Problem Description: I encountered an ImportError when attempting to execute the `weight_diff.py` script from the Stanford Alpaca project for applying a weight differential....

I want to use the alpaca-7b model, but it seems it doesn't provide the model. Based on my understanding, from the information provided, I need to first get the llama-7b...

I am working on a replication paper of Alpaca and would appreciate being able to accurately replicate your results for how you prompted Alpaca and which Self-instruct instructions you used...

So far with the example of fine tuning I see examples of summarisation, chatbot based on specific use cases etc. However, I want to build the a chatbot based on...

https://github.com/tatsu-lab/stanford_alpaca/blob/761dc5bfbdeeffa89b8bff5d038781a4055f796a/train.py#L90-L99 In this snippet of code, from what I understand, the padding is not added since using "longest" mode on a single sequence is equivalent to adding no paddings as...

File "***/train/sft/finetune_clm.py", line 156, in __post_init__ if type(self.target_modules)==str: AttributeError: 'ModelArguments' object has no attribute 'target_modules' Is it a code snippet accidentally introduced in finetune_clm.py? It seems to be better to...

I'm trying to train the alpaca model using python 3.10. But when I try to train, there is always a bug here: ```Traceback (most recent call last): File "./stanford_alpaca/weight_diff.py", line...

Hi, Thank you for the great work! I am applying Alpaca's method to other domains. But I encountered some issues when utilizing the `regen.json` (generated by `generate_instruction.py`). Could you provide...

Hi I finetuned the llama 7b model using alpaca. Below is the command I ran. ``` CUDA_VISIBLE_DEVICES=2 torchrun --nproc_per_node=1 --master_port=8090 train.py \ --model_name_or_path ./model/weight/7B \ --data_path /home/sulki/project/devops/my_own_data.json \ --bf16 True...

Hi, Many thanks for releasing this repo for using LLM on local machine! We just have two quick questions about the model. 1. Could we know if the Python bindings...