gorilla
RWKV-LM
gorilla | RWKV-LM | |
---|---|---|
51 | 84 | |
10,118 | 11,657 | |
- | - | |
8.9 | 8.8 | |
3 days ago | 7 days ago | |
Python | Python | |
Apache License 2.0 | Apache License 2.0 |
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.
gorilla
-
Launch HN: Nango (YC W23) – Open-Source Unified API
Do you leverage https://gorilla.cs.berkeley.edu/ at all? If not, perhaps consider if it would solve some pain for you.
- Autonomous LLM agents with human-out-of-loop
- Show HN: I made a script to scrape your Facebook group
-
Pushing ChatGPT's Structured Data Support to Its Limits
* Gorilla [https://github.com/ShishirPatil/gorilla]
Could be interesting to try some of these exercises with these models.
-
Guidance for selecting a function-calling library?
gorilla
- Gorilla: An API Store for LLMs
-
Show HN: OpenAPI DevTools – Chrome ext. that generates an API spec as you browse
Nice this made me go back and check up on the Gorilla LLM project [1] to see whats they are doing with API and if they have applied their fine tuning to any of the newer foundation models but looks like things have slowed down since they launched (?) or maybe development is happening elsewhere on some invisible discord channel but I hope the intersection of API calling and LLM as a logic processing function keep getting focus it's an important direction for interop across the web.
[1] https://github.com/ShishirPatil/gorilla
-
RestGPT
"Gorilla: Large Language Model Connected with Massive APIs" (2023) https://gorilla.cs.berkeley.edu/ :
> Gorilla enables LLMs to use tools by invoking APIs. Given a natural language query, Gorilla comes up with the semantically- and syntactically- correct API to invoke. With Gorilla, we are the first to demonstrate how to use LLMs to invoke 1,600+ (and growing) API calls accurately while reducing hallucination. We also release APIBench, the largest collection of APIs, curated and easy to be trained on! Join us, as we try to expand the largest API store and teach LLMs how to write them!
eval/:
- Calling APIs with Natural Language
-
Shishir Patil: Teaching AI to Use APIs with Gorilla LLM – Humans of AI Podcast
Humans of AI Podcast #7
An amazing conversation with Shishir Patil the creator of the Gorilla LLM, a large language model specifically trained to use APIs!
Shishir is currently a 5th year PhD student at the University of California, Berkeley whose work broadly covers ML-Systems, LLMs, Edge-ML, and Sky computing.
Definitely give the episode a listen to hear Shishir's story.
And to read more about #GorillaLLM, check out the project page!
https://gorilla.cs.berkeley.edu
RWKV-LM
-
Do LLMs need a context window?
https://github.com/BlinkDL/RWKV-LM#rwkv-discord-httpsdiscord... lists a number of implementations of various versions of RWKV.
https://github.com/BlinkDL/RWKV-LM#rwkv-parallelizable-rnn-w... :
> RWKV: Parallelizable RNN with Transformer-level LLM Performance (pronounced as "RwaKuv", from 4 major params: R W K V)
> RWKV is an RNN with Transformer-level LLM performance, which can also be directly trained like a GPT transformer (parallelizable). And it's 100% attention-free. You only need the hidden state at position t to compute the state at position t+1. You can use the "GPT" mode to quickly compute the hidden state for the "RNN" mode.
> So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding (using the final hidden state).
> "Our latest version is RWKV-6,*
- People who've used RWKV, whats your wishlist for it?
- Paving the way to efficient architectures: StripedHyena-7B
-
Understanding Deep Learning
That is not true. There are RNNs with transformer/LLM-like performance. See https://github.com/BlinkDL/RWKV-LM.
-
Q-Transformer: Scalable Reinforcement Learning via Autoregressive Q-Functions
This is what RWKV (https://github.com/BlinkDL/RWKV-LM) was made for, and what it will be good at.
Wow. Pretty darn cool! <3 :'))))
-
Personal GPT: A tiny AI Chatbot that runs fully offline on your iPhone
Thanks for the support! Two weeks ago, I'd have said longer contexts on small on-device LLMs are at least a year away, but developments from last week seem to indicate that it's well within reach. Once the low hanging product features are done, I think it's a worthy problem to spend a couple of weeks or perhaps even months on. Speaking of context lengths, recurrent models like RWKV technically have infinite context lengths, but in practice the context slowly fades away after a few thousands of tokens.
-
"If you see a startup claiming to possess top-secret results leading to human level AI, they're lying or delusional. Don't believe them!" - Yann LeCun, on the conspiracy theories of "X company has reached AGI in secret"
This is the reason there are only a few AI labs, and they show little of the theoretical and scientific understanding you believe is required. Go check their code, there's nothing there. Even the transformer with it's heads and other architectural elements turns out to not do anything and it is less efficient than RNNs. (see https://github.com/BlinkDL/RWKV-LM)
-
The Secret Sauce behind 100K context window in LLMs: all tricks in one place
I've been pondering the same thing, as simply extending the context window in a straightforward manner would lead to a significant increase in computational resources. I've had the opportunity to experiment with Anthropics' 100k model, and it's evident that they're employing some clever techniques to make it work, albeit with some imperfections. One interesting observation is that their prompt guide recommends placing instructions after the reference text when inputting lengthy text bodies. I noticed that the model often disregarded the instructions if placed beforehand. It's clear that the model doesn't allocate the same level of "attention" to all parts of the input across the entire context window.
Moreover, the inability to cache transformers makes the use of large context windows quite costly, as all previous messages must be sent with each call. In this context, the RWKV-LM project on GitHub (https://github.com/BlinkDL/RWKV-LM) might offer a solution. They claim to achieve performance comparable to transformers using an RNN, which could potentially handle a 100-page document and cache it, thereby eliminating the need to process the entire document with each subsequent query. However, I suspect RWKV might fall short in handling complex tasks that require maintaining multiple variables in memory, such as mathematical computations, but it should suffice for many scenarios.
On a related note, I believe Anthropics' Claude is somewhat underappreciated. In some instances, it outperforms GPT4, and I'd rank it somewhere between GPT4 and Bard overall.
-
Meta's plan to offer free commercial AI models puts pressure on Google, OpenAI
> The only reason open-source LLMs have a heartbeat is they’re standing on Meta’s weights.
Not necessarily.
RWKV, for example, is a different architecture that wasn't based on Facebook's weights whatsoever. I don't know where BlinkDL (the author) got the training data, but they seem to have done everything mostly independently otherwise.
https://github.com/BlinkDL/RWKV-LM
disclaimer: I've been doing a lot of work lately on an implementation of CPU inference for this model, so I'm obviously somewhat biased since this is the model I have the most experience in.
-
Eliezer Yudkowsky - open letter on AI
I think the main concern is that, due to the resources put into LLM research for finding new ways to refine and improve them, that work can then be used by projects that do go the extra mile and create things that are more than just LLMs. For example, RWKV is similar to an LLM but will actually change its own model after every processed token, thus letting it remember things longer-term without the use of 'context tokens'.
What are some alternatives?
DB-GPT - AI Native Data App Development framework with AWEL(Agentic Workflow Expression Language) and Agents
llama - Inference code for Llama models
Voyager - An Open-Ended Embodied Agent with Large Language Models
alpaca-lora - Instruct-tune LLaMA on consumer hardware
gorilla-cli - LLMs for your CLI
flash-attention - Fast and memory-efficient exact attention
Gin - Gin is a HTTP web framework written in Go (Golang). It features a Martini-like API with much better performance -- up to 40 times faster. If you need smashing performance, get yourself some Gin.
koboldcpp - A simple one-file way to run various GGML and GGUF models with KoboldAI's UI
GirlfriendGPT - Girlfriend GPT is a Python project to build your own AI girlfriend using ChatGPT4.0
gpt4all - gpt4all: run open-source LLMs anywhere
SuperAGI - <⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.
RWKV-CUDA - The CUDA version of the RWKV language model ( https://github.com/BlinkDL/RWKV-LM )