AgentTuning: Enabling Generalized Agent Abilities for LLMsAgentTuning: Enabling Generalized Agent Abilities For LLMs π€ Model (AgentLM-70B) β’ π€ Dataset (AgentInstruct) β’ π Paper β’ π Project Page δΈζη(Chinese) AgentTuning represents the very first attempt to instruction-tune LLMs using interaction trajectories across multiple agent tasks. Evaluation results indicate that AgentTuning enables the agent capabilities of LLMs with robust generalization on unseen agent tasks while remaining good on β¦
Free ChatGPT 3.5 / ChatGPT 4 / Free OpenAI API Π ΡΡΡΠΊΠΈΠΉ | English The project is currently undergoing a transition to another client and reconstruction of the API. Technical work is continuing. We apologize for any inconvenience. Free API service providing access to GPT-3.5, GPT-4, and other language models. Before using it, please make sure you check out our wiki. The project utilizes a modified version of gpt4free, as well as ChuanhuChatGPT as a web interface. We extend our gratitudeβ¦
The Startup CTO's Handbook, a book covering leadership, management and technical topics for leaders of software engineering teams NOTE: As of October 2023 I'm still working on porting the book content into markdown. Everything is in there (via a .doc to .md auto-converter) but the formatting is all over the place and needs a lot of cleanup still, apologies for my mess in the interim! The Book You can view the latest content of the book in markdown here You can buy the book on amazon (Coβ¦
Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models"Eureka: Human-Level Reward Design via Coding Large Language Models [Website] [arXiv] [PDF] eureka_zoomout.mp4 Large Language Models (LLMs) have excelled as high-level semantic planners for sequential decision-making tasks. However, harnessing them to learn complex low-level manipulation tasks, such as dexterous pen spinning, remains an open problem. We bridge tβ¦
ΠΠΊΡΠΏΠ΅ΡΡΡ Β«ΠΠ°Π±ΠΎΡΠ°ΡΠΎΡΠΈΠΈ ΠΠ°ΡΠΏΠ΅ΡΡΠΊΠΎΠ³ΠΎΒ» ΠΎΠ±Π½Π°ΡΡΠΆΠΈΠ»ΠΈ ΠΊΠΈΠ±Π΅ΡΡΠΏΠΈΠΎΠ½ΡΠΊΡΡ ΠΊΠ°ΠΌΠΏΠ°Π½ΠΈΡ, ΠΏΠΎΠ»ΡΡΠΈΠ²ΡΡΡ Π½Π°Π·Π²Π°Π½ΠΈΠ΅ TetrisPhantom ΠΈ Π½Π°ΠΏΡΠ°Π²Π»Π΅Π½Π½ΡΡ Π½Π° Π³ΠΎΡΡΠ΄Π°ΡΡΡΠ²Π΅Π½Π½ΡΠ΅ ΠΎΡΠ³Π°Π½ΠΈΠ·Π°ΡΠΈΠΈ Π² ΠΠ·ΠΈΠ°ΡΡΠΊΠΎ-Π’ΠΈΡ ΠΎΠΎΠΊΠ΅Π°Π½ΡΠΊΠΎΠΌ ΡΠ΅Π³ΠΈΠΎΠ½Π΅. Π₯Π°ΠΊΠ΅ΡΡ ΠΈΡΠΏΠΎΠ»ΡΠ·ΠΎΠ²Π°Π»ΠΈ ΡΠΊΠΎΠΌΠΏΡΠΎΠΌΠ΅ΡΠΈΡΠΎΠ²Π°Π½Π½ΡΠΉ Π·Π°ΡΠΈΡΠ΅Π½Π½ΡΠΉ USB-Π½Π°ΠΊΠΎΠΏΠΈΡΠ΅Π»Ρ ΠΎΠΏΡΠ΅Π΄Π΅Π»Π΅Π½Π½ΠΎΠ³ΠΎ ΡΠΈΠΏΠ°, ΠΊΠΎΡΠΎΡΡΠΉ ΠΎΠ±ΡΡΠ½ΠΎ ΠΏΡΠΈΠΌΠ΅Π½ΡΠ΅ΡΡΡ Π΄Π»Ρ Π±Π΅Π·ΠΎΠΏΠ°ΡΠ½ΠΎΠ³ΠΎ Ρ ΡΠ°Π½Π΅Π½ΠΈΡ Π΄Π°Π½Π½ΡΡ .
ΠΠΎΡΠ»Π΅ ΡΠΎΠ³ΠΎ ΠΊΠ°ΠΊ Π½Π° ΠΏΡΠΎΡΠ»ΠΎΠΉ Π½Π΅Π΄Π΅Π»Π΅ ΠΏΡΠ°Π²ΠΎΠΎΡ ΡΠ°Π½ΠΈΡΠ΅Π»ΡΠ½ΡΠ΅ ΠΎΡΠ³Π°Π½Ρ Π·Π°Ρ Π²Π°ΡΠΈΠ»ΠΈ ΡΠ°ΠΉΡΡ Π²ΡΠΌΠΎΠ³Π°ΡΠ΅Π»ΡΡΠΊΠΎΠΉ Π³ΡΡΠΏΠΏΠΈΡΠΎΠ²ΠΊΠΈ Ragnar Locker, ΠΏΡΠ΅Π΄ΡΡΠ°Π²ΠΈΡΠ΅Π»ΠΈ ΠΠ²ΡΠΎΠΏΠΎΠ»Π° ΡΠΎΠΎΠ±ΡΠΈΠ»ΠΈ, ΡΡΠΎ Β«ΠΊΠ»ΡΡΠ΅Π²Π°Ρ ΡΠ΅Π»ΡΒ», ΡΠ²ΡΠ·Π°Π½Π½Π°Ρ Ρ ΡΡΠΎΠΉ Ρ Π°ΠΊ-Π³ΡΡΠΏΠΏΠΎΠΉ, Π±ΡΠ»Π° Π°ΡΠ΅ΡΡΠΎΠ²Π°Π½Π° Π² ΠΠ°ΡΠΈΠΆΠ΅.
ΠΠ»Ρ ΠΏΠΎΠ΄ΠΏΠΈΡΡΠΈΠΊΠΎΠ²Π ΡΡΠΎΠΉ ΡΡΠ°ΡΡΠ΅ ΠΌΡ ΠΏΠΎΠ»ΡΡΠΈΠΌ Π΄ΠΎΡΡΡΠΏ ΠΊΒ Π²Π΅Π±βΡΠ΅ΡΠ²Π΅ΡΡ ΡΠ΅ΡΠ΅Π· RCE-ΡΡΠ·Π²ΠΈΠΌΠΎΡΡΡ ΠΈΒ ΡΠΊΡΠΏΠ»ΡΠ°ΡΠ°ΡΠΈΡ SQL-ΠΈΠ½ΡΠ΅ΠΊΡΠΈΠΈ Π²Β PostgreSQL. ΠΠ°ΡΠ΅ΠΌ Π²ΠΎΡΠΏΠΎΠ»ΡΠ·ΡΠ΅ΠΌΡΡ ΡΡΠ΅ΠΉΠΌΠ²ΠΎΡΠΊΠΎΠΌ Jupyter Π΄Π»ΡΒ Π²ΡΠΏΠΎΠ»Π½Π΅Π½ΠΈΡ ΠΏΡΠΎΠΈΠ·Π²ΠΎΠ»ΡΠ½ΠΎΠ³ΠΎ ΠΊΠΎΠ΄Π° ΠΈΒ ΠΏΠΎΠ²ΡΡΠΈΠΌ ΠΏΡΠΈΠ²ΠΈΠ»Π΅Π³ΠΈΠΈ Π²Β SatTrack.
ΠΡΡΠΏΠ½ΡΠΉ ΠΏΠΎΡΡΠ°Π²ΡΠΈΠΊ ΡΠΈΡΡΠ΅ΠΌ ΡΠΏΡΠ°Π²Π»Π΅Π½ΠΈΡ Π΄ΠΎΡΡΡΠΏΠΎΠΌ ΠΈ ΠΈΠ΄Π΅Π½ΡΠΈΡΠΈΠΊΠ°ΡΠΈΠ΅ΠΉ, ΠΊΠΎΠΌΠΏΠ°Π½ΠΈΡ Okta, Π²Π½ΠΎΠ²Ρ ΡΠΎΠΎΠ±ΡΠ°Π΅Ρ ΠΎ Π²Π·Π»ΠΎΠΌΠ΅. ΠΠ° ΡΡΠΎΡ ΡΠ°Π· Ρ Π°ΠΊΠ΅ΡΡ ΠΈΡΠΏΠΎΠ»ΡΠ·ΠΎΠ²Π°Π»ΠΈ ΡΠΊΡΠ°Π΄Π΅Π½Π½ΡΠ΅ ΡΡΠ΅ΡΠ½ΡΠ΅ Π΄Π°Π½Π½ΡΠ΅ ΠΈ ΠΏΠΎΠ»ΡΡΠΈΠ»ΠΈ Π΄ΠΎΡΡΡΠΏ ΠΊ ΡΠ°ΠΉΠ»Π°ΠΌ, ΡΠΎΠ΄Π΅ΡΠΆΠ°ΡΠΈΠΌ cookie ΠΈ ΡΠΎΠΊΠ΅Π½Ρ ΡΠ΅Π°Π½ΡΠΎΠ², ΠΊΠΎΡΠΎΡΡΠ΅ ΠΊΠ»ΠΈΠ΅Π½ΡΡ ΠΊΠΎΠΌΠΏΠ°Π½ΠΈΠΈ Π·Π°Π³ΡΡΠΆΠ°Π»ΠΈ Π² ΡΠΈΡΡΠ΅ΠΌΡ ΡΠΏΡΠ°Π²Π»Π΅Π½ΠΈΡ ΠΏΠΎΠ΄Π΄Π΅ΡΠΆΠΊΠΎΠΉ.
ΠΡΠΎΠ΄ΠΎΠ»ΠΆΠ°Π΅ΡΡΡ Π½Π°Π±ΠΎΡ Π½Π° ΠΊΡΡΡΡ ΠΏΠΎ IT ΠΈ ΠΈΠ½ΡΠΎΡΠΌΠ°ΡΠΈΠΎΠ½Π½ΠΎΠΉ Π±Π΅Π·ΠΎΠΏΠ°ΡΠ½ΠΎΡΡΠΈ Π² ΠΠΊΠ°Π΄Π΅ΠΌΠΈΠ΅ΠΉ ΠΠΎΠ΄Π΅Π±Π°ΠΉ. Π Π½ΠΎΡΠ±ΡΠ΅ ΡΡΠ°ΡΡΡΡΡ ΡΡΠ°Π·Ρ ΡΠ΅ΡΡΡΠ΅ Π½ΠΎΠ²ΡΡ ΠΏΠΎΡΠΎΠΊΠ° ΠΏΠΎ Π½Π΅ΡΠΊΠΎΠ»ΡΠΊΠΈΠΌ Π½Π°ΠΏΡΠ°Π²Π»Π΅Π½ΠΈΡΠΌ: ΡΠ°Π·Π²Π΅Π΄ΠΊΠ° open source, ΠΏΡΠΎΠ³ΡΠ°ΠΌΠΌΠΈΡΠΎΠ²Π°Π½ΠΈΠ΅, ΡΠ΅Π²Π΅ΡΡ-ΠΈΠ½ΠΆΠΈΠ½ΠΈΡΠΈΠ½Π³ ΠΈ ΠΊΠΈΠ±Π΅ΡΠ±Π΅Π·ΠΎΠΏΠ°ΡΠ½ΠΎΡΡΡ.