Difference between revisions of "Toolformer"
m |
m |
||
| Line 36: | Line 36: | ||
* We then use a self-supervised loss to determine which of these API calls actually help the model in predicting future tokens. | * We then use a self-supervised loss to determine which of these API calls actually help the model in predicting future tokens. | ||
* Finally, we finetune the LM itself on the API calls that it considers useful. | * Finally, we finetune the LM itself on the API calls that it considers useful. | ||
| + | |||
| + | |||
<hr> | <hr> | ||
Revision as of 13:31, 16 March 2023
YouTube search... ...Google search
- 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
- Assistants ... Hybrid Assistants ... Agents ... Negotiation
- Natural Language Processing (NLP) ...Generation ...LLM ...Tools & Services
- Python ... Generative AI with Python ... Javascript ... Generative AI with Javascript ... Game Development with Generative AI
- Generative AI ... OpenAI's ChatGPT ... Perplexity ... Microsoft's BingAI ... You ...Google's Bard
- Attention Mechanism/Transformer Model
- Prompt Engineering (PE) ...PromptBase ... Prompt Injection Attack
- Proximal Policy Optimization (PPO)
- Natural Language Generation (NLG)
- 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 ...
- Meta AI and UPF Researchers Introduce Toolformer: A Language Model That Learns in a Self-Supervised Way How to Use Different Tools Such as Search Engines via Simple API Calls | Khushboo Gupta - MarketTechPost
The Toolformer methodology uses in-context learning techniques as its foundation to create complete datasets from scratch. 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
- Q&A system
- search engine
- translation system
- 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.
- Given just a handful of human-written examples of how an API can be used, we let a language model (LM) annotate a huge language modeling dataset with potential API calls.
- We then use a self-supervised loss to determine which of these API calls actually help the model in predicting future tokens.
- Finally, we finetune the LM itself on the API calls that it considers useful.
In machine learning, self-supervised learning is a type of training technique that does not require manually labeled training data. Instead, the algorithm is trained on a different, related task that serves as a supervisory signal. A self-supervised loss function is used to calculate the difference between the predicted output and the actual output, with the goal of minimizing this difference during training.
In the context of self-supervised learning, a self-supervised loss is a type of loss function that is used to train a predictive model based on a self-supervised task. A self-supervised loss function is designed to take advantage of the supervisory signal provided by the self-supervised task, which allows the algorithm to learn representative features of the data that can be used for downstream tasks. The precise form of the self-supervised loss function depends on the specifics of the self-supervised task being used, but typically involves minimizing the difference between the predicted output and the actual output.
|
|
|
|
