Contributions de Jboscher

Aller à la navigation Aller à la recherche
Rechercher des contributionsaffichermasquer
⧼contribs-top⧽
⧼contribs-date⧽

(les plus récentes | les plus anciennes) Voir (50 plus récentes | ) (20 | 50 | 100 | 250 | 500)

19 septembre 2023

  • 09:3319 septembre 2023 à 09:33 diff hist +208 N AI AgentPage créée avec « AI agents are artificial entities that sense their environment, make decisions, and take actions. The Rise and Potential of Large Language Model Based Agents: A Survey : https://arxiv.org/pdf/2309.07864.pdf » actuelle

1 août 2023

  • 12:101 août 2023 à 12:10 diff hist +709 SFTAucun résumé des modifications actuelle
  • 12:001 août 2023 à 12:00 diff hist +404 N SFTPage créée avec « Supervised Fine-Tuning (SFT): Models are trained on a dataset of instructions and responses. It adjusts the weights in the LLM to minimize the difference between the generated answers and ground-truth responses, acting as labels. == Références == * [https://towardsdatascience.com/fine-tune-your-own-llama-2-model-in-a-colab-notebook-df9823a04a32] Fine-Tune Your Own Llama 2 Model in a Colab Notebook »

27 juillet 2023

  • 09:3427 juillet 2023 à 09:34 diff hist +373 N PEFTPage créée avec « Thus, we, as a com- munity of researchers and engineers, need efficient ways to train on downstream task data. Parameter-efficient fine-tuning, which we denote as PEFT, aims to resolve this problem by only training a small set of parameters which might be a subset of the existing model parameters or a set of newly added parameters. https://arxiv.org/pdf/2303.15647.pdf » actuelle

5 juillet 2023

  • 21:195 juillet 2023 à 21:19 diff hist 0 AgentAucun résumé des modifications actuelle
  • 21:185 juillet 2023 à 21:18 diff hist +1 406 N AgentPage créée avec « In LangChain, agents are high-level components that use language models (LLMs) to determine which actions to take and in what order. An action can either be using a tool and observing its output or returning it to the user. Tools are functions that perform specific duties, such as Google Search, database lookups, or Python REPL. Agents involve an LLM making decisions about which Actions to take, taking that Action, seeing an Observation, and repeating that until... »

4 juillet 2023

  • 10:154 juillet 2023 à 10:15 diff hist +393 TemperatureAucun résumé des modifications actuelle
  • 10:144 juillet 2023 à 10:14 diff hist +169 Prompt designAucun résumé des modifications actuelle
  • 10:134 juillet 2023 à 10:13 diff hist +228 Zero-shotAucun résumé des modifications actuelle
  • 10:124 juillet 2023 à 10:12 diff hist +179 Prompt designAucun résumé des modifications
  • 09:204 juillet 2023 à 09:20 diff hist +681 N Prompt designPage créée avec « Please note a few best practices around prompt design. Be concise Be specific and well-defined Ask one task at a time Turn generative tasks into classification tasks. For example, instead of asking what programming language to learn, ask if Python, Java, or C is a better fit for a beginner in programming. and Improve response quality by including examples. Adding instructions and a few examples tends to yield good results however there’s currently no one best w... »
  • 08:584 juillet 2023 à 08:58 diff hist +2 571 N Zero-shotPage créée avec « Zero-shot prompting - is a method where the LLM is given no additional data on the specifictask that it is being asked to perform. Instead, it is only given a prompt that describes the task. For example, if you want the LLM to answer a question, you just prompt "what is prompt design?". One-shot prompting - is a method where the LLM is given a single example of the task that it is being asked to perform. For example, if you want the LLM to write a poem, you might... »

22 juin 2023

  • 08:3022 juin 2023 à 08:30 diff hist +3 088 N Top PPage créée avec « First, there are different models you can choose from. Each model is tuned to perform well on specific tasks. You can also specify the temperature, top P, and top K. These parameters all adjust the randomness of responses by controlling how the output tokens are selected. When you send a prompt to the model, it produces an array of probabilities over the words that could come next. And from this array, we need some strategy to decide what to return. A simple stra... » actuelle
  • 08:2822 juin 2023 à 08:28 diff hist +2 291 N Top KPage créée avec « First, there are different models you can choose from. Each model is tuned to perform well on specific tasks. You can also specify the temperature, top P, and top K. These parameters all adjust the randomness of responses by controlling how the output tokens are selected. When you send a prompt to the model, it produces an array of probabilities over the words that could come next. And from this array, we need some strategy to decide what to return. A simple stra... » actuelle
  • 08:2422 juin 2023 à 08:24 diff hist +1 620 N TemperaturePage créée avec « First, there are different models you can choose from. Each model is tuned to perform well on specific tasks. You can also specify the temperature, top P, and top K. These parameters all adjust the randomness of responses by controlling how the output tokens are selected. When you send a prompt to the model, it produces an array of probabilities over the words that could come next. And from this array, we need some strategy to decide what to return. A simple stra... »

11 mai 2023

2 mai 2023

1 mai 2023

  • 08:021 mai 2023 à 08:02 diff hist +43 N Fichier:Cropped-cropped-LogoBackPropTrans-300x120-3.pngLogo BackProp transparent actuelle
  • 07:361 mai 2023 à 07:36 diff hist −1 PromptAucun résumé des modifications
  • 07:331 mai 2023 à 07:33 diff hist +833 PromptAucun résumé des modifications
  • 07:291 mai 2023 à 07:29 diff hist +548 N PromptPage créée avec «  == Références == * [https://learn.microsoft.com/en-us/azure/cognitive-services/openai/concepts/prompt-engineering] Introduction to prompt engineering * [https://www.deeplearning.ai/short-courses/chatgpt-prompt-engineering-for-developers/] ChatGPT Prompt Engineering for Developers * [https://learn.microsoft.com/en-us/azure/cognitive-services/openai/concepts/advanced-prompt-engineering?pivots=programming-language-chat-completions] Prompt engineering techniques... »

27 avril 2023

22 janvier 2023

12 janvier 2023

10 janvier 2023

(les plus récentes | les plus anciennes) Voir (50 plus récentes | ) (20 | 50 | 100 | 250 | 500)