supercharger
E2B
supercharger | E2B | |
---|---|---|
13 | 35 | |
346 | 6,164 | |
- | 3.9% | |
6.6 | 9.9 | |
about 1 year ago | about 24 hours ago | |
Python | TypeScript | |
MIT License | 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.
supercharger
-
Claude 2
Since I've been on a AI code-helper kick recently. According to the post, Claude 2 now 71.2%, a significant upgrade from 1.3 (56.0%). It isn't specified whether this is pass@1 or pass@10.
For comparison:
* GPT-4 claims 85.4 on HumanEval, in a recent paper https://arxiv.org/pdf/2303.11366.pdf GPT-4 was tested at 80.1 pass@1 and 91 pass@1 using their Reflexion technique. They also include MBPP and Leetcode Hard benchmark comparisons
* WizardCoder, a StarCoder fine-tune is one of the top open models, scoring a 57.3 pass@1, model card here: https://huggingface.co/WizardLM/WizardCoder-15B-V1.0
* The best open model I know of atm is replit-code-instruct-glaive, a replit-code-3b fine tune, which scores a 63.5% pass@1. An independent developer abacaj has reproduced that announcement as part of code-eval, a repo for getting human-eval results: https://github.com/abacaj/code-eval
Those interested in this area may also want to take a look at this repo https://github.com/my-other-github-account/llm-humaneval-ben... that also ranks with Eval+, the CanAiCode Leaderboard https://huggingface.co/spaces/mike-ravkine/can-ai-code-resul... and airate https://github.com/catid/supercharger/tree/main/airate
Also, as with all LLM evals, to be taken with a grain of salt...
Liu, Jiawei, Chunqiu Steven Xia, Yuyao Wang, and Lingming Zhang. βIs Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation.β arXiv, June 12, 2023. https://doi.org/10.48550/arXiv.2305.01210.
- Let's be honest: none of the models can code well
-
April 2023
Leverage locally-hosted Large Language Models to write software + unit tests (https://github.com/catid/supercharger)
- What coding llm is the best?
-
Is there such a thing as local Llamas integrated into VSCode?
supercharger Write Software + unit tests for you, based on Baize-30B 8bit, using model parallelism
- I have a project in my own programming language, abusing both lexical and syntactic macros. I want to do a refactoring tasks on it. I don't have a GPU, but 14-core CPU. Should I pay for cloud or there are local ways to do such task on my laptop? Which model is better for programming?
- What is the best open source model/program to help index and debug code?
- Leverage locally-hosted Large Language Models to write software and unit tests
-
Can LLMs do static code analysis?
Added support for 65B LLaMa model to https://github.com/catid/supercharger tonight. It runs faster than Baize 30B (maybe due to lack of adapter) and only slightly slower than Galpaca 30B. Benchmarks here: https://docs.google.com/spreadsheets/d/1TYBNr_UPJ7wCzJThuk5ysje7K1x-_62JhBeXDbmrjA8/edit?usp=sharing
-
Benchmarks for LLMs on Consumer Hardware
Here's the code that loads it: https://github.com/catid/supercharger/blob/main/server/model_koala.py
E2B
-
Ask HN: Who is hiring? (May 2024)
E2B | https://e2b.dev | San Francisco, CA | Full-time | In-person
[E2B](https://e2b.dev) is building a secure open-source runtime that will power next billion of AI apps & agents.
We found an early traction with making it easy for developers to add [code interpreting](https://github.com/e2b-dev/code-interpreter) to their AI apps with our SDK built on top of our [agentic runtime](https://github.com/e2b-dev/e2b). We have paying customers from seed to enterprise companies.
We're hiring:
- Frontend/Product Engineer
- Infrastructure Engineer
Check the roles here https://e2b.dev/careers
-
Show HN: Add AI code interpreter to any LLM via SDK
Hi, I'm the CEO of the company that built this SDK.
We're a company called E2B [0]. We're building and open-source [1] secure environments for running untrusted AI-generated code and AI agents. We call these environments sandboxes and they are built on top of micro VM called Firecracker [2].
You can think of us as giving small cloud computers to LLMs.
We recently created a dedicated SDK for building custom code interpreters in Python or JS/TS. We saw this need after a lot of our users have been adding code execution capabilities to their AI apps with our core SDK [3]. These use cases were often centered around AI data analysis so code interpreter-like behavior made sense
The way our code interpret SDK works is by spawning an E2B sandbox with Jupyter Server. We then communicate with this Jupyter server through Jupyter Kernel messaging protocol [4].
We don't do any wrapping around LLM, any prompting, or any agent-like framework. We leave all of that on users. We're really just a boring code execution layer that sats at the bottom that we're building specifically for the future software that will be building another software. We work with any LLM. Here's how we added code interpreter to Claude [5].
Our long-term plan is to build an automated AWS for AI apps and agents.
Happy to answer any questions and hear feedback!
[0] https://e2b.dev/
[1] https://github.com/e2b-dev
[2] https://github.com/firecracker-microvm/firecracker
[3] https://e2b.dev/docs
[4] https://jupyter-client.readthedocs.io/en/latest/messaging.ht...
[5] https://github.com/e2b-dev/e2b-cookbook/blob/main/examples/c...
- Open Source Python Code Interpreter for Any LLM
- Show HN: Open-Source Infrastructure for AI Code Interpreters
-
We're building cloud runtime for AI agents and gradually open-sourcing everything
Hey folks, we're building an open source runtime for AI agents at E2B.
- Show HN: Run LLM-generated code in sandboxed envs
- Sandboxed cloud environments for AI agents & apps with a single line of code
- We're building a cloud for AI agents & AI apps, It's free and we're gradually open-sourcing the infra. Would love to hear your feedback!
- [P] We're building a cloud for AI agents & AI apps, It's free and we're gradually open-sourcing the infra. Would love to hear your feedback!
What are some alternatives?
developer - the first library to let you embed a developer agent in your own app!
Auto-GPT - An experimental open-source attempt to make GPT-4 fully autonomous. [Moved to: https://github.com/Significant-Gravitas/Auto-GPT]
gptest - GPTest VS Code Extension
chatgpt-shell - ChatGPT and DALL-E Emacs shells + Org babel π¦ + a shell maker for other providers
walter - AI-powered software development assistant built right into GitHub so it can act as your junior developer.
IncognitoPilot - An AI code interpreter for sensitive data, powered by GPT-4 or Code Llama / Llama 2.
llm-humaneval-benchmarks
Selefra - The open-source policy-as-code software that provides analysis for Multi-Cloud and SaaS environments, you can get insight with natural language (powered by OpenAI).
evaporate - This repo contains data and code for the paper "Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes"
JARVIS - JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
locai - Connect to Kobold API through VS Code
telegram-chatgpt-concierge-bot - Interact with OpenAI's ChatGPT via Telegram and Voice.