info
gpt-neo
info | gpt-neo | |
---|---|---|
75 | 82 | |
322 | 6,158 | |
1.6% | - | |
3.8 | 7.3 | |
19 days ago | about 2 years ago | |
JavaScript | Python | |
GNU General Public License v3.0 only | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
info
-
AWS and Blockchain
https://info.uniswap.org/
Uniswap alone clears this amount. Part of the power of decentralized exchanges is that every trade is logged and publicly available, which is not something you can claim for their centralized counterparts.
-
97.7% of tokens launched on Uniswap were scams and rug pulls
"No one goes there anymore, it's too popular!"
Yesterday over $2.1B in volume cleared on Uniswap [0]. It's certainly useable by someone. If you want cheaper fees, try it on Arbitrum or Optimism.
[0] - https://info.uniswap.org/#/
-
Tether will not freeze Tornado Cash addresses
Somebody would! (Or rather, some thing.) There are a lot of smartcontract liquidity pools in Ethereum that facilitate trade between two tokens. The set an exchange rate by a formula that only looks at how much of each token is currently in the pool, not at prevailing market price[1].
So if and when it's apparent that Tether will be worthless, there will be a mad dash to dump it in those LPs in exchange for the other tokens, which was what happened to TerraUSD [2].
Here's a list of the LPs that have Tether as one token, just on Uniswap:
https://info.uniswap.org/#/tokens/0xdac17f958d2ee523a2206206...
[1] This as the effect of writing a persistent ITM option by the extent to which the LP's price diverge's from the market exchange rate.
[2] Here's Curve's infamous 4pool, which has TerraUSD (UST) and three other non-defunct stablecoins -- it's 97% UST now: https://curve.fi/4pool
-
What is the smartest anti crypto argument you've ever heard?
A quick look at some code on Uniswap, for example, shows that they use TheGraph for their statistics services - there would be no reasonable way to handle this data otherwise.
-
Web3 is just expensive P2P
Coinbase is a centralized exchange. Of course it runs in a SQL db or whatever. They only need to touch the chain when settling inflows/outflows.
But something like Uniswap: https://app.uniswap.org/#/swap is fully on-chain. Every trade happens on chain, because the application is an immutable smart contract liquidity protocol, called an AMM, or automated market maker.
It does as much, if not more, volume than Coinbase ($1.98B in last 24H): https://info.uniswap.org/#/
-
Token Info Site
Is there an Info Site for JunoSwap, like "info.osmosis.zone" or "info.uniswap.org". Thanks!
-
How do you view limit orders?
Go to info.uniswap.org and search for Hex and select the pool you want to look at. In the "liquidity" tab you can see how much Hex/other coin is available for buy/sell at each price level. It defaults to uniswap V3 but you can manually select V2 in the top right and do the same.
-
Run interface and v3-info on local geth node
how can one run interface (app.uniswap.org) and v3-info (info.uniswap.org) on the local computer, and to set provider as local node, for example geth, and not "be connected" to some external node provider? I want to be fully on my own if:
-
The Promise of DAOs, the Latest Craze in Crypto
Fun fact: after the DAO had essentially folded, the $PEOPLE token folks were left holding could be traded for more than 10X the value it cost to go in on the DAO.
To this day, it still trades for ~10X its initial value on Uniswap: https://info.uniswap.org/#/tokens/0x7a58c0be72be218b41c608b7...
Anyone who bought more than ~$50 of DAO tokens before the auction could stand to make a profit on the aftermarket even accounting for gas fees.
In case it needs to be said: this all seems crazy to me, but it is what it is.
-
My DeFi strategy in 2022 - Critique me!
And REF won't diversify across the entire L1. The REF coin staking is a bet on trading volume, not on price, and it's quite possible for coins in the ecosystem to go up in price without a lot of trading volume. If anything, a downward market causes more trading volume than an upward market: look at the graph on the right side of this page and you'll see more volume the last few days due to panic trading than in any previous weeks.
gpt-neo
-
How Open is Generative AI? Part 2
By December 2020, EleutherAI had introduced The Pile, a comprehensive text dataset designed for training models. Subsequently, tech giants such as Microsoft, Meta, and Google used this dataset for training their models. In March 2021, they revealed GPT-Neo, an open-source model under Apache 2.0 license, which was unmatched in size at its launch. EleutherAI’s later projects include the release of GPT-J, a 6 billion parameter model, and GPT-NeoX, a 20 billion parameter model, unveiled in February 2022. Their work demonstrates the viability of high-quality open-source AI models.
-
Creating an open source chat bot like ChatGPT for my own dataset without GPU?
Yeah, if that is your requirement you should definitely ignore chatterbot, as its older and probably not what your teacher wants. I'm looking at the gpt-neo docs right now: https://github.com/EleutherAI/gpt-neo
-
Any real competitor to GPT-3 which is open source and downloadable?
3.) EleutherAI's GPT-Neo and GPT-NeoX: EleutherAI is an independent research organization that aims to promote open research in artificial intelligence. They have released GPT-Neo, an open-source language model based on the GPT architecture, and are developing GPT-NeoX, a highly-scalable GPT-like model. You can find more information on their GitHub repositories: GPT-Neo: https://github.com/EleutherAI/gpt-neo GPT-NeoX: https://github.com/EleutherAI/gpt-neox
-
⚡ Neural - AI Code Generation for Vim
This is one of the first comprehensive plugins that has been rewritten to support multiple AI backends such as OpenAI GPT3+ and other custom sources in the future such as ChatGPT, GPT-J, GPT-neo and more.
-
Looks like some Taliban fighters are getting burnt out working the 9-5 grind
GPT-Neo is newer than GPT-2 on the open source side of things. In my experience, it tends to give longer and more creative responses than GPT-2 but not on the level of GPT-3. I've not tried GPT-J or GPT-NeoX, but they're also open source and reportedly better than GPT-Neo (albeit less accessible).
- H3 - a new generative language models that outperforms GPT-Neo-2.7B with only *2* attention layers! In H3, the researchers replace attention with a new layer based on state space models (SSMs). With the right modifications, they find that it can outperform transformers.
- First Open Source Alternative to ChatGPT Has Arrived
-
Where is the line for AI and where does ChatGPT stand?
Finally, yes-- it is trained via masked language modeling (text prediction). The approach has been fairly standard for years- the big difference with the GPT* models is the number of paramaters and volume of text-- we still haven't reached a ceiling with LLM parameters- they appear to keep improving with size. This training allows the model to learn a strong representation of language. Their training approach is published and open-source GPT* versions have already been made and released (https://github.com/EleutherAI/gpt-neo). However, the models are huge and can't be run locally for hobbyists. This gets at larger issues in democratization of ML.
- Using the GPT-3 AI Writer inside Obsidian(This is COOL)
-
Teaser trailer for "The Diary of Sisyphus" (2023), the world's first feature film written by an artificial intelligence (GPT-NEO) and produced Briefcase Films, my indie film studio based in Northern Italy
- GPT-Neo 2.7B, released Mar/2021, and unmaintained/unsupported as of Aug/2021? or;
What are some alternatives?
crypto-fees - Website for comparing total daily fees of various blockchain protocols.
gpt-neox - An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
RatioGang.com
haystack - :mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
reach-lang - Reach: The Safest and Smartest DApp Programming Language
openchat - OpenChat: Easy to use opensource chatting framework via neural networks
v3-core - 🦄 🦄 🦄 Core smart contracts of Uniswap v3
tensorflow - An Open Source Machine Learning Framework for Everyone
web3j - Lightweight Java and Android library for integration with Ethereum clients
mesh-transformer-jax - Model parallel transformers in JAX and Haiku
graph-node - Graph Node indexes data from blockchains such as Ethereum and serves it over GraphQL
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.