MAJOR UPDATE: Remove CCS, VINC

[AlexTMallen]

This PR does several major things to the repository:

• It removes support for CCS and VINC, and removes the use of contrast pairs
• The InferenceServer class is used to do inference, enabling FSDP (--fsdp) inference with much larger models
  • It also only requires loading the model once, and doesn't load the model if the dataset is cached
• Only support LR probes and LM predictions
• LM predictions are taken in response to statement + suffix where statement is the statement we're extracting hidden states from and suffix is a piece of text like "\n\nIs the above statement true or false?" that's optionally specified in the yaml template file
• logprobs are optionally stored with --save_logprobs
• support for non-balanced datasets with --balance False
• Added testing for:
  • The pipeline that turns the raw HF dataset into the input_ids dataset passed to InferenceServer
  • InferenceServer
• default template called "_default" which takes the "statement" column itself

[norabelrose]

almost good to go

[norabelrose]

I think we should probably just get rid of this. If we really want to explore the half-space of admissible predictors we should probably try the Conical Knowledge Decomposition thing.

[AlexTMallen]

I have actually been using this occasionally, basically it just gives me a higher recall way of searching for good probes. Do you still think we should get rid of it?

[norabelrose]

let's drop this

[AlexTMallen]

I have actually been using this occasionally, basically it just gives me a higher recall way of searching for good probes. Do you still think we should get rid of it?

[norabelrose]

let's merge this bad boy