modal-labs / doppel-bot Goto Github PK

View Code? Open in Web Editor NEW

204.0 204.0 27.0 26 KB

Train a language model to answer Slack messages as you.

Home Page: https://modal.com/docs/guide/slack-finetune

License: MIT License

Python 100.00%

ai artificial-intelligence language-model python pytorch slack-bot

doppel-bot's People

Contributors

Stargazers

Watchers

doppel-bot's Issues

Shouldn't `generate_prompt(data_point["instruction"], data_point["input"])` be `generate_prompt(data_point["user"], data_point["input"])`

I was going through the codebase for training llama2 on Modal, and I saw the option here, to train the model only on the labels, and I think since we want to mask out the tokens which corresponds to the user and the input, the code mentioned here

should be

user_prompt = generate_prompt(data_point["user"], data_point["input"])

instead of

user_prompt = generate_prompt(data_point["instruction"], data_point["input"])

Update Link in repository description

Current link in the description leads to 404.

Change require

From:
https://modal.com/docs/guide/slack-finetune

To:
https://modal.com/docs/examples/slack-finetune

NotImplementedError: Loading a dataset cached in a LocalFileSystem is not supported.

Running modal run src.finetune --user="<user>" is giving error:

Dataset json downloaded and prepared to file:///root/.cache/huggingface/datasets/json/default-18a2e225bb973cb6/0.0.0/0f7e3662623656454fcd2b650f34e886a7db4b9104504885bd462096cc7a9f51. Subsequent calls will reuse thTraceback (most recent call last):
  File "/pkg/modal/_container_entrypoint.py", line 342, in handle_input_exception
    yield
  File "/pkg/modal/_container_entrypoint.py", line 460, in run_inputs
    res = imp_fun.fun(*args, **kwargs)
  File "/root/src/finetune.py", line 249, in finetune
    data = load_dataset("json", data_files=data_path)
  File "/opt/conda/lib/python3.9/site-packages/datasets/load.py", line 1794, in load_dataset
    ds = builder_instance.as_dataset(split=split, verification_mode=verification_mode, in_memory=keep_in_memory)
  File "/opt/conda/lib/python3.9/site-packages/datasets/builder.py", line 1089, in as_dataset
    raise NotImplementedError(f"Loading a dataset cached in a {type(self._fs).__name__} is not supported.")
NotImplementedError: Loading a dataset cached in a LocalFileSystem is not supported.

It may be due to pinning to an older version of the hf datasets library "datasets==2.10.1" as described in this SO post

DeprecationError: Deprecated on 2023-08-16: `f.call(...)` is deprecated. It has been renamed to `f.remote_gen(...)`

I ran modal run src.finetune --user="<user>" and got this error:

Beginning scrape for <user> in ...
Traceback (most recent call last):
  File "/pkg/modal/_container_entrypoint.py", line 342, in handle_input_exception
    yield
  File "/pkg/modal/_container_entrypoint.py", line 460, in run_inputs
    res = imp_fun.fun(*args, **kwargs)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/src/scrape.py", line 168, in scrape
    channel_ids = list(get_channel_ids.call(bot_token))
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/pkg/synchronicity/synchronizer.py", line 497, in proxy_method
    return wrapped_method(instance, *args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/pkg/synchronicity/combined_types.py", line 24, in __call__
    return self._func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/pkg/synchronicity/synchronizer.py", line 398, in f_wrapped
    res = f(*args, **kwargs)
          ^^^^^^^^^^^^^^^^^^
  File "/pkg/modal/functions.py", line 1158, in call
    deprecation_error(
  File "/pkg/modal/exception.py", line 96, in deprecation_error
    raise DeprecationError(f"Deprecated on {deprecated_on}: {msg}")
modal.exception.DeprecationError: Deprecated on 2023-08-16: `f.call(...)` is deprecated. It has been renamed to `f.remote_gen(...)`
Beginning scrape for <user> in ...
Traceback (most recent call last):
  File "/pkg/modal/_container_entrypoint.py", line 342, in handle_input_exception
    yield
  File "/pkg/modal/_container_entrypoint.py", line 460, in run_inputs
    res = imp_fun.fun(*args, **kwargs)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/src/scrape.py", line 168, in scrape
    channel_ids = list(get_channel_ids.call(bot_token))
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/pkg/synchronicity/synchronizer.py", line 497, in proxy_method
    return wrapped_method(instance, *args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/pkg/synchronicity/combined_types.py", line 24, in __call__
    return self._func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/pkg/synchronicity/synchronizer.py", line 398, in f_wrapped
    res = f(*args, **kwargs)
          ^^^^^^^^^^^^^^^^^^
  File "/pkg/modal/functions.py", line 1158, in call
    deprecation_error(
  File "/pkg/modal/exception.py", line 96, in deprecation_error
    raise DeprecationError(f"Deprecated on {deprecated_on}: {msg}")
modal.exception.DeprecationError: Deprecated on 2023-08-16: `f.call(...)` is deprecated. It has been renamed to `f.remote_gen(...)`
Beginning scrape for <user> in ...
Traceback (most recent call last):
  File "/pkg/modal/_container_entrypoint.py", line 342, in handle_input_exception
    yield
  File "/pkg/modal/_container_entrypoint.py", line 460, in run_inputs
    res = imp_fun.fun(*args, **kwargs)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/src/scrape.py", line 168, in scrape
    channel_ids = list(get_channel_ids.call(bot_token))
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/pkg/synchronicity/synchronizer.py", line 497, in proxy_method
    return wrapped_method(instance, *args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/pkg/synchronicity/combined_types.py", line 24, in __call__
    return self._func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/pkg/synchronicity/synchronizer.py", line 398, in f_wrapped
    res = f(*args, **kwargs)
          ^^^^^^^^^^^^^^^^^^
  File "/pkg/modal/functions.py", line 1158, in call
    deprecation_error(
  File "/pkg/modal/exception.py", line 96, in deprecation_error
    raise DeprecationError(f"Deprecated on {deprecated_on}: {msg}")
modal.exception.DeprecationError: Deprecated on 2023-08-16: `f.call(...)` is deprecated. It has been renamed to `f.remote_gen(...)`
Beginning scrape for <user> in ...
Traceback (most recent call last):
  File "/pkg/modal/_container_entrypoint.py", line 342, in handle_input_exception
    yield
  File "/pkg/modal/_container_entrypoint.py", line 460, in run_inputs
    res = imp_fun.fun(*args, **kwargs)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/src/scrape.py", line 168, in scrape
    channel_ids = list(get_channel_ids.call(bot_token))
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/pkg/synchronicity/synchronizer.py", line 497, in proxy_method
    return wrapped_method(instance, *args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/pkg/synchronicity/combined_types.py", line 24, in __call__
    return self._func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/pkg/synchronicity/synchronizer.py", line 398, in f_wrapped
    res = f(*args, **kwargs)
          ^^^^^^^^^^^^^^^^^^
  File "/pkg/modal/functions.py", line 1158, in call
    deprecation_error(
  File "/pkg/modal/exception.py", line 96, in deprecation_error
    raise DeprecationError(f"Deprecated on {deprecated_on}: {msg}")
modal.exception.DeprecationError: Deprecated on 2023-08-16: `f.call(...)` is deprecated. It has been renamed to `f.remote_gen(...)`

ValueError: A100 20GB is unsupported, consider A10 or A100 40GB instead

Running modal run src.inference --user="<user>" gives error:

ValueError: A100 20GB is unsupported, consider A10 or A100 40GB instead

Default base model

Has this been attempted with a different base model? Seems like mistral 7B or at least llama 2 might be a better starting place now. If you think it'd be a simple replacement in the configuration, I'm happy to try it out and submit a PR

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.