Logan

as_strided() error

10

I've noticed a few people encountering issues like this: ``` Traceback (most recent call last): File "train.py", line 121, in con.train(model[args.model_name], args.save_name) File "C:\Users\logan\Documents\mitacs2\LSR\code\config\ConfigBert.py", line 740, in train predict_re =...

Pretrained model release?

2

Are you able to publish the pre-trained model from the paper? It would save a lot of time for others wanting to test this model 😄

Are you able to post or release the pretrained models from the paper? It would be helpful for those of us that don't have big enough GPUs to train 😆

I'm using a custom prompt_helper, as follows: ``` # define prompt helper # set number of output tokens num_output = 512 # set maximum input size max_input_size = 2048 #...

Knowledge Graph Sources?

2

Love the new support for knowledge graph triplets! I'm working on possibly augmenting the triplets with previously extracted triplets from dedicated methods (i.e. relation extraction, openIE). Is there any way...

Add Option for Knowledge Graph Similarities

2

This PR adds support for using embedding similarities within the knowledge graph index. You may have noticed that relying purely on keyword mapping for finding relation tuples may result in...

improve agent ux with chatgpt

1

This is a minor change to the agent. If "Action Input" and "Action" is not parsed from the llm_output, then assume that no tool is needed. Frequently, ChatGPT will not...

Add "refresh" functionality to existing indexes

2

I saw this mentioned in https://github.com/jerryjliu/gpt_index/issues/262 and thought it sounded useful (and fun!) It's a little tricky, because once a document is inserted into an index, we lose most context...

Add support for prepending messages with Chat models

2

This has been a pretty frequently requested feature. This will support both ChatGPT and other models like davinci I know the `ChatGPTLLMPredictor` supported this, but I think that's deprecated now...

Driver versions needed?

6

Does this not support AMD GPUs? I'm getting this error: ``` terminate called after throwing an instance of 'tvm::runtime::InternalError' what(): [18:53:29] /home/runner/work/utils/utils/tvm/src/runtime/vulkan/vulkan_instance.cc:111: --------------------------------------------------------------- An error occurred during the execution of...