ChrisHayduk

"""

The code below combines approaches published by both @eugene-yh and @jinyongyoo on Github. 

Thanks for the contributions guys!

"""

import torch
import peft

cpursley

PostgreSQL is Enough

• Simplify: move code into database functions
• Just Use Postgres for Everything
• PostgreSQL is the worlds’ best database
• Postgres is eating the database world
• Hacker News discussion

Background and Cron Jobs

the-crypt-keeper

#
# this is adapted from https://github.com/facebookresearch/llama/blob/main/llama/generation.py#L213
# the tokenizer is replaced with ord() to make it easier to see whats actually happening

from typing_extensions import TypedDict, Literal
from typing import List, Optional

Role = Literal["system", "user", "assistant"]

class Message(TypedDict):

jaretburkett

smiling mouth revealing white straight teeth - 24426
anxious expression with biting lower lip - 17012
shallow depth of field - 16806
early childhood age - 14067
social worker - 12566
smiling mouth revealing slightly crooked teeth - 12329
broad grin revealing straight white teeth - 11336
pediatrician - 11212
preschooler age - 10873
headshot - 10462

yoavg

Reinforcement Learning for Language Models

Yoav Goldberg, April 2023.

Why RL?

With the release of the ChatGPT model and followup large language models (LLMs), there was a lot of discussion of the importance of "RLHF training", that is, "reinforcement learning from human feedback". I was puzzled for a while as to why RL (Reinforcement Learning) is better than learning from demonstrations (a.k.a supervised learning) for training language models. Shouldn't learning from demonstrations (or, in language model terminology "instruction fine tuning", learning to immitate human written answers) be sufficient? I came up with a theoretical argument that was somewhat convincing. But I came to realize there is an additional argumment which not only supports the case of RL training, but also requires it, in particular for models like ChatGPT. This additional argument is spelled out in (the first half of) a talk by John Schulman from OpenAI. This post pretty much

moyix

Using Linear Algebra to Convert a Large Code Model

Background

The SalesForce CodeGen models are a family of large language models trained on a large amount of natural language data and then fine-tuned on specialized datasets of code. Models of size 350M, 2B, 6B, and 16B parameters are provided in three flavors:

• nl, the base model trained on The Pile, a large natural language dataset compiled by EleutherAI
• multi, which is fine-tuned from the nl model on a dataset of code in multiple languages, scraped from GitHub, and
• mono, which is fine-tuned from the multi model on Python code only.

tomholford

Installing pg gem on macOS

If you're trying to install the postgresql gem pg and it is failing with the following error message:

Installing pg 1.2.3 with native extensions
Gem::Ext::BuildError: ERROR: Failed to build gem native extension.

    current directory: ~/.rbenv/versions/3.0.0/lib/ruby/gems/3.0.0/gems/pg-1.2.3/ext
~/.rbenv/versions/3.0.0/bin/ruby -I ~/.rbenv/versions/3.0.0/lib/ruby/3.0.0 -r ./siteconf20210125-97201-pycpo.rb extconf.rb

raorao

Any top-level comment on pull request ought be tagged with one of four emojis:

• ❓ for a non-blocking comment that asks for clarification. The pull request author must answer the question before the pull request is merged, but does not have to wait for the comment author to re-review before merging.

• 🎨 for a non-blocking comment that proposes a refactor or cleanup. The pull request author does not have to address the comment for the pull request to merge.

• ⚠️ for a blocking comment that must be addressed before the pull request can merge. The comment's author should leave a Request Changes review, and is responsible for re-reviewing once the pull request author has addressed the issue.

• 😻 for a comment that compliments the author for their work.

laser

data Failable t e = Success t | Failure e

augustj

#!/bin/bash
#

# testflightapp.com tokens

# This one is per user (and is August's)
API_TOKEN="XXX"

TEAM_TOKEN="XXX"
PRODUCT_NAME="myAppName"