Difference between revisions of "Toolformer"
m |
m |
||
| Line 9: | Line 9: | ||
* [[Assistants]] ... [[Hybrid Assistants]] ... [[Agents]] ... [[Negotiation]] | * [[Assistants]] ... [[Hybrid Assistants]] ... [[Agents]] ... [[Negotiation]] | ||
| + | * [[Python]] ... [[Generative AI with Python]] ... [[Javascript]] ... [[Generative AI with Javascript]] ... [[Game Development with Generative AI]] | ||
* [[Attention]] Mechanism/[[Transformer]] Model | * [[Attention]] Mechanism/[[Transformer]] Model | ||
* [[Prompt Engineering (PE)]] ...[[Prompt Engineering (PE)#PromptBase|PromptBase]] ... [[Prompt Injection Attack]] | * [[Prompt Engineering (PE)]] ...[[Prompt Engineering (PE)#PromptBase|PromptBase]] ... [[Prompt Injection Attack]] | ||
Revision as of 08:44, 8 March 2023
YouTube search... ...Google search
- Assistants ... Hybrid Assistants ... Agents ... Negotiation
- Python ... Generative AI with Python ... Javascript ... Generative AI with Javascript ... Game Development with Generative AI
- Attention Mechanism/Transformer Model
- Prompt Engineering (PE) ...PromptBase ... Prompt Injection Attack
- Proximal Policy Optimization (PPO)
- Natural Language Generation (NLG)
- Natural Language Tools & Services
- Meta
- Toolformer: Language Models Can Teach Themselves to Use Tools | T. Schick, J. Dwivedi-Yu, R. Dessì, R. Raileanu, M. Lomeli, L. Zettlemoyer, N. Cancedda, & T. Scialom .. Language models (LMs) can teach themselves to use external tools via simple APIs and achieve the best of both worlds
- Meta develops an AI language bot that can use external software tools | Benj Edwards - Ars Technica ... With Toolformer, an LLM can improve its abilities by calling APIs to external programs ...
Toolformer is a model trained by Meta AI to decide which APIs to call, when to call them, what arguments to pass, and how to best incorporate the results into future token prediction. This is done in a self-supervised way, requiring nothing more than a handful of demonstrations for each API. They incorporate a range of tools, including a calculator, a Q&A system, a search engine, a translation system, and a calendar. Toolformer achieves substantially improved zero-shot performance across a variety of downstream tasks, often competitive with much larger models, without sacrificing its core language modeling abilities
|
|
|
|