Abhinav M Kulkarni

Results 52 comments of Abhinav M Kulkarni

With regards to training a new model with custom data, yes, it is indeed possible to do so. I would recommend first training a zero-shot learning (zeshel) model first just...

@shzamanirad: The training data for crossencoder is output by `eval_biencoder.py` script. For every datapoint in train/test/valid split, the eval script basically outputs top 64 retrieved candidates and calculates recall at...

I set up a local instance of TGI and added it in `config.py` as follows: ```python from continuedev.src.continuedev.libs.llm.ht_tgi import HuggingFaceTGI ... config=ContinueConfig( ... models=Models( default=HuggingFaceTGI(server_url="http://localhost:8080") ) ) ``` Please note,...

Thanks @sestinj, I now get a new error: ```python Traceback (most recent call last): File "continuedev/src/continuedev/libs/util/create_async_task.py", line 21, in callback future.result() File "asyncio/futures.py", line 203, in result File "asyncio/tasks.py", line...

Thanks @sestinj, local TGI setup works and I can generate responses from it. However, I am not able to feed it context by selecting code, please see the attached video....

Also, for Llama 2 models, `` is a special token that indicates end of text/sequence and should not be displayed. You can see in the following attached image, that is...

Thanks, @sestinj, here's a video screengrab for a simple prompt. This is the full prompt and the response: ``` This is a log of the prompt/completion pairs sent/received from the...

Thanks, @sestinj, things work perfectly now, except for one small detail. The title generated seems to be random and has nothing to do with the prompt. I am attaching an...

Hey @sestinj, > Also relevant for now might be the "disable_summaries" option in config.py Thanks, that works. > Which model are you using? I am using a [4-bit AWQ quantized](https://huggingface.co/abhinavkulkarni/codellama-CodeLlama-7b-Instruct-hf-w4-g128-awq)...

@clintoncheang: Have you looked at [`eval_biencoder.py`](https://github.com/facebookresearch/BLINK/blob/main/blink/biencoder/eval_biencoder.py) script?