Tous les journaux publics

Affichage combiné de tous les journaux disponibles sur Wiki BackProp. Vous pouvez personnaliser l’affichage en sélectionnant le type de journal, le nom d’utilisateur ou la page concernée (ces deux derniers étant sensibles à la casse).

• 19 septembre 2023 à 09:33 Jboscher discussion contributions a créé la page AI Agent (Page 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 »)
• 1 août 2023 à 12:00 Jboscher discussion contributions a créé la page SFT (Page 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 à 09:34 Jboscher discussion contributions a créé la page PEFT (Page 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 »)
• 5 juillet 2023 à 21:18 Jboscher discussion contributions a créé la page Agent (Page 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 à 09:20 Jboscher discussion contributions a créé la page Prompt design (Page 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... »)
• 4 juillet 2023 à 08:58 Jboscher discussion contributions a créé la page Zero-shot (Page 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 à 08:30 Jboscher discussion contributions a créé la page Top P (Page 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... »)
• 22 juin 2023 à 08:28 Jboscher discussion contributions a créé la page Top K (Page 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... »)
• 22 juin 2023 à 08:24 Jboscher discussion contributions a créé la page Temperature (Page 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 à 03:30 Jboscher discussion contributions a créé la page LangChain (Page créée avec «  == Références == * [https://python.langchain.com/en/latest/index.html] Documentation LangChain * [https://www.youtube.com/watch?v=2xxziIWmaSA&list=PLqZXAkvF1bPNQER9mLmDbntNfSpzdDIU5&index=4] Cours LangChain »)
• 2 mai 2023 à 09:25 Jboscher discussion contributions a créé la page LLaMA (Page créée avec « LLaMA (Large Language Model Meta AI) is a language model released by Meta (Facebook). It is Meta’s answer to OpenAI’s GPT models. Like GPT, LLaMA is intended to be a general-purpose foundational model suitable for further fine-tuning. [1] == Références == * [https://agi-sphere.com/llama-models/] A brief history of LLaMA models »)
• 1 mai 2023 à 08:02 Jboscher discussion contributions a téléversé Fichier:Cropped-cropped-LogoBackPropTrans-300x120-3.png (Logo BackProp transparent)
• 1 mai 2023 à 08:02 Jboscher discussion contributions a créé la page Fichier:Cropped-cropped-LogoBackPropTrans-300x120-3.png (Logo BackProp transparent)
• 1 mai 2023 à 07:29 Jboscher discussion contributions a créé la page Prompt (Page 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 à 16:36 Jboscher discussion contributions a téléversé Fichier:Capture d’écran 2023-04-27 à 18.32.50.png (A comparative illustration of in-context learning (ICL) and chain-of-thought (CoT) prompting)
• 27 avril 2023 à 16:36 Jboscher discussion contributions a créé la page Fichier:Capture d’écran 2023-04-27 à 18.32.50.png (A comparative illustration of in-context learning (ICL) and chain-of-thought (CoT) prompting)
• 27 avril 2023 à 16:35 Jboscher discussion contributions a créé la page In-context learning (Page créée avec «  [1] The in-context learning (ICL) ability is formally introduced by GPT-3 : assuming that the language model has been provided with a natural language instruction and/or several task demonstrations, it can generate the expected output for the test instances by completing the word sequence of input text, without requiring additional training or gradient update == Références == * [https://arxiv.org/pdf/2303.18223.pdf] A Survey of Large Language Models »)
• 27 avril 2023 à 15:39 Jboscher discussion contributions a créé la page Emergent Abilities of Large Language Models (Page créée avec « On entend par "Emergent Abilities of Large Language Models" une capacité présente dans un LLM qui ne se retrouve pas dans un modèle similaire mais plus petit. Ce qui veut dire aussi qu'on ne peut pas prévoir (extrapoler) cette nouvelle capacité uniquement à partir de celles d'un modèle plus petit. [1] We consider an ability to be emergent if it is not present in smaller models but is present in larger models. Although scaling is mainly conducted in mode... »)
• 27 avril 2023 à 14:44 Jboscher discussion contributions a créé la page Pre-trained language models (Page créée avec « Les auteurs de "A Survey of Large Language Models" distinguent les "Pre-trained language models (PLM)" des Large language models (LLM). ELMo et BERT appartiendraient à la 1ère catégorie, un peu comme les pionniers des LLM. As an early attempt, ELMo was proposed to capture context-aware word representations by first pre-training a bidirectional LSTM (biLSTM) network (instead of learning fixed word representations) and then fine-tuning the biLSTM network acco... »)
• 27 avril 2023 à 13:31 Jboscher discussion contributions a téléversé Fichier:Cropped-LogoBackPropTrans-2.png (Logo BackProp)
• 27 avril 2023 à 13:31 Jboscher discussion contributions a créé la page Fichier:Cropped-LogoBackPropTrans-2.png (Logo BackProp)
• 27 avril 2023 à 13:29 Jboscher discussion contributions a créé la page Fichier:Shamentality artificial intelligence beautiful textures and ter 545b2bf2-aece-4268-b49e-78dee7f78862.png (AI logo by MidJourney)
• 27 avril 2023 à 13:29 Jboscher discussion contributions a téléversé Fichier:Shamentality artificial intelligence beautiful textures and ter 545b2bf2-aece-4268-b49e-78dee7f78862.png (AI logo by MidJourney)
• 22 janvier 2023 à 21:59 Jboscher discussion contributions a créé la page Reinforcement Learning from Human Feedback (Page créée avec « Reinforcement Learning from Human Feedback (RLHF) https://huggingface.co/blog/rlhf »)
• 10 janvier 2023 à 14:23 Jboscher discussion contributions a créé la page Classifier Free Guidance (Page créée avec « By default, the model doesn't often do what we ask. If we want it to follow the prompt better, we use a hack called CFG. There's a good explanation in this video (AI coffee break GLIDE). In the code, this comes down to us doing: noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond) This works suprisingly well :) Explore changing the guidance_scale in the code above and see how this affects the results. How high can you push it be... »)
• 5 janvier 2023 à 13:54 Jboscher discussion contributions a créé la page Dreambooth (Page créée avec « Dreambooth is a kind of fine-tuning that attempts to introduce new subjects by providing just a few images of the new subject. The goal is similar to that of Textual Inversion, but the process is different. Instead of creating a new token as Textual Inversion does, we select an existing token in the vocabulary (usually a rarely used one), and fine-tune the model for a few hundred steps to bring that token close to the images we provide. This is a regular fine-tun... »)
• 4 janvier 2023 à 09:02 Jboscher discussion contributions a créé la page Generative model (Page créée avec « « A generative model describes how a dataset is generated, in terms of a probabilistic model. By sampling from this model, we are able to generate new data. » Extrait de Generative Deep Learning David Foster »)
• 13 décembre 2022 à 09:11 Jboscher discussion contributions a créé la page Tesla A100 (Page créée avec « D'après Nvidia : The A100 80GB debuts the world’s fastest memory bandwidth at over 2 terabytes per second (TB/s) to run the largest models and datasets. le A100 est beaucoup plus rapide que le V100 https://www.nvidia.com/en-us/data-center/a100/ »)
• 13 décembre 2022 à 09:06 Jboscher discussion contributions a créé la page Tesla V100 (Page créée avec « Tesla V100 est nettement moins performant que le A100. Voir le benchmark de Lambda sur le sujet : A100 Vs V100 Deep Learning Benchmarks https://lambdalabs.com/blog/nvidia-a100-vs-v100-benchmarks »)
• 8 décembre 2022 à 09:28 Jboscher discussion contributions a créé la page Textual Inversion (Page créée avec « Textual Inversion est défini de la façon suivante : "We learn to generate specific concepts, like personal objects or artistic styles, by describing them using new "words" in the embedding space of pre-trained text-to-image models. These can be used in new sentences, just like any other word." == Références == * [https://textual-inversion.github.io] »)
• 8 novembre 2022 à 10:18 Jboscher discussion contributions a créé la page ImageNet (Page créée avec « The ImageNet dataset, one of the largest efforts in this space, required over 25,000 workers to annotate 14 million images for 22,000 object categories »)
• 8 novembre 2022 à 09:27 Jboscher discussion contributions a créé la page CLIP (Page créée avec « Références - CLIP: Connecting Text and Images - A Beginner’s Guide to the CLIP Model »)