Hugging Face - Revision history

BPeat at 01:15, 27 April 2024

2024-04-27T01:15:47Z

BPeat at 15:31, 13 September 2023

2023-09-13T15:31:03Z

BPeat at 00:49, 17 August 2023

2023-08-17T00:49:02Z

BPeat at 10:36, 31 July 2023

2023-07-31T10:36:28Z

BPeat at 16:12, 30 June 2023

2023-06-30T16:12:54Z

BPeat at 00:46, 27 June 2023

2023-06-27T00:46:06Z

BPeat: /* Hugging Face's Open-source Library */

2023-06-15T10:55:55Z

‎Hugging Face's Open-source Library

BPeat at 10:34, 15 June 2023

2023-06-15T10:34:23Z

BPeat at 10:31, 15 June 2023

2023-06-15T10:31:10Z

BPeat at 10:29, 15 June 2023

2023-06-15T10:29:44Z

@@ Line 20: / Line 20: @@
 [https://www.bing.com/news/search?q=ai+Hugging+Face...X&qft=interval%3d%228%22 ...Bing News]
 * [https://huggingface.co/ Hugging Face] ... The AI community building the future
 * [https://huggingface.co/models Models | Hugging Face] ... click on Sort: Trending

@@ Line 22: / Line 22: @@
 * [https://huggingface.co/ Hugging Face] ... The AI community building the future
 * [https://huggingface.co/models Models | Hugging Face] ... click on Sort: Trending
-* [[Embedding]] ... [[Fine-tuning]] ... [[Agents#AI-Powered Search|Search]] ... [[Clustering]] ... [[Recommendation]] ... [[Anomaly Detection]] ... [[Classification]] ... [[Dimensional Reduction]].  [[...find outliers]]
+* [[Embedding]] ... [[Fine-tuning]] ... [[Retrieval-Augmented Generation (RAG)|RAG]] ... [[Agents#AI-Powered Search|Search]] ... [[Clustering]] ... [[Recommendation]] ... [[Anomaly Detection]] ... [[Classification]] ... [[Dimensional Reduction]].  [[...find outliers]]
 * [[Platforms: AI/Machine Learning as a Service (AIaaS/MLaaS)]]
 * [https://www.youtube.com/watch?v=00GKzGyWFEs&list=PLo2EIpI_JMQvWfQndUesu0nPBAtZ9gP1o Hugging Face course]

@@ Line 22: / Line 22: @@
 * [https://huggingface.co/ Hugging Face] ... The AI community building the future
 * [https://huggingface.co/models Models | Hugging Face] ... click on Sort: Trending
 * [[Platforms: AI/Machine Learning as a Service (AIaaS/MLaaS)]]
 * [https://www.youtube.com/watch?v=00GKzGyWFEs&list=PLo2EIpI_JMQvWfQndUesu0nPBAtZ9gP1o Hugging Face course]
@@ Line 64: / Line 65: @@
 LightGPT is a language model developed by AWS Contributors. It is based on GPT-J 6B and was instruction fine-tuned on the high-quality, Apache-2.0 licensed OIG-small-chip instruction dataset with ~200K training examples. The model is designed to generate text based on a given instruction, and it can be deployed to [[Amazon]] [[SageMaker]]
-GPT-J 6B is a transformer model trained using Ben Wang's Mesh Transformer JAX. "GPT-J" refers to the class of model, while "6B" represents the number of trainable parameters. The model consists of 28 layers with a model dimension of 4096, and a feedforward dimension of 16384. The model dimension is split into 16 heads, each with a dimension of 256. Rotary Position [[Embedding]] (RoPE) is applied to 64 dimensions of each head. The model is trained with a tokenization vocabulary of 50257, using the same set of BPEs as GPT-2/GPT-3. GPT-J learns an inner representation of the English language that can be used to extract features useful for downstream tasks. The model is best at what it was pretrained for however, which is generating text from a prompt. GPT-J-6B is not intended for deployment without fine-tuning, supervision, and/or moderation. It is not a product in itself and cannot be used for human-facing interactions. For example, the model may generate harmful or offensive text. Please evaluate the risks associated with your particular use case.
+GPT-J 6B is a transformer model trained using Ben Wang's Mesh Transformer JAX. "GPT-J" refers to the class of model, while "6B" represents the number of trainable parameters. The model consists of 28 layers with a model dimension of 4096, and a feedforward dimension of 16384. The model dimension is split into 16 heads, each with a dimension of 256. Rotary Position [[Embedding]] (RoPE) is applied to 64 dimensions of each head. The model is trained with a tokenization vocabulary of 50257, using the same set of BPEs as GPT-2/GPT-3. GPT-J learns an inner representation of the English language that can be used to extract features useful for downstream tasks. The model is best at what it was pretrained for however, which is generating text from a prompt. GPT-J-6B is not intended for deployment without [[fine-tuning]], supervision, and/or moderation. It is not a product in itself and cannot be used for human-facing interactions. For example, the model may generate harmful or offensive text. Please evaluate the risks associated with your particular use case.
 == <span id="Whisper"></span>Whisper ==
 <youtube>8xYYvO7LGBw</youtube>

@@ Line 21: / Line 21: @@
 * [https://huggingface.co/ Hugging Face] ... The AI community building the future
 * [[Platforms: AI/Machine Learning as a Service (AIaaS/MLaaS)]]
 * [https://www.youtube.com/watch?v=00GKzGyWFEs&list=PLo2EIpI_JMQvWfQndUesu0nPBAtZ9gP1o Hugging Face course]

@@ Line 2: / Line 2: @@
 |title=PRIMO.ai
 |titlemode=append
-|keywords=artificial, intelligence, machine, learning, models, algorithms, data, singularity, moonshot, Tensorflow, Google, Nvidia, Microsoft, Azure, Amazon, AWS
+|keywords=ChatGPT, artificial, intelligence, machine, learning, GPT-4, GPT-5, NLP, NLG, NLC, NLU, models, data, singularity, moonshot, Sentience, AGI, Emergence, Moonshot, Explainable, TensorFlow, Google, Nvidia, Microsoft, Azure, Amazon, AWS, Hugging Face, OpenAI, Tensorflow, OpenAI, Google, Nvidia, Microsoft, Azure, Amazon, AWS, Meta, LLM, metaverse, assistants, agents, digital twin, IoT, Transhumanism, Immersive Reality, Generative AI, Conversational AI, Perplexity, Bing, You, Bard, Ernie, prompt Engineering LangChain, Video/Image, Vision, End-to-End Speech, Synthesize Speech, Speech Recognition, Stanford, MIT |description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools
 |description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools
 }}
 [https://www.youtube.com/results?search_query=ai+Hugging+Face YouTube]

@@ Line 38: / Line 38: @@
 == <span id="Hugging Face's Open-source Library"></span>Hugging Face's Open-source Library ==
-Hugging Face's open-source library, Transformers, is widely used for natural language processing tasks. The company also offers an Inference API that allows developers to serve their models directly from Hugging Face infrastructure and run large scale NLP models in milliseconds with just a few lines of code. Hugging Face offers a wide range of machine learning models and datasets, as well as tools for building, training, and deploying state-of-the-art models.
+Hugging Face's open-source library, Transformers, is widely used for [[Natural Language Processing (NLP)]]  tasks. The company also offers an Inference API that allows developers to serve their models directly from Hugging Face infrastructure and run large scale [[[[Natural Language Processing (NLP)|NLP]] models in milliseconds with just a few lines of code. Hugging Face offers a wide range of machine learning models and datasets, as well as tools for building, training, and deploying state-of-the-art models.
 == <span id="Private Hub"></span>Private Hub ==

@@ Line 18: / Line 18: @@
 Hugging Face is an American company that develops tools for building applications using machine learning. It is most notable for its transformers library built for natural language processing applications and its platform that allows users to share machine learning models and datasets. Hugging Face is a community and a platform for artificial intelligence and data science that aims to democratize AI knowledge and assets used in AI models. The platform allows users to build, train and deploy state of the art models powered by open source machine learning. It also provides a place where a broad community of data scientists, researchers, and ML engineers can come together and share ideas, get support and contribute to open source projects. Is there anything else you would like to know? - [https://en.wikipedia.org/wiki/Hugging_Face Wikipedia]
 <youtube>agwbNgxwkHc</youtube>
 <youtube>QEaBAZQCtwE</youtube>
-== Hugging Face Community ==
+= Hugging Face Community =
 * [https://towardsdatascience.com/whats-hugging-face-122f4e7eb11a What's Hugging Face? An AI community for sharing ML models and datasets]
 * [[Agents#HuggingGPT|HuggingGPT]]   ... in partnership with [[Microsoft]]
@@ Line 37: / Line 37: @@
 Their platform is home to a large community of developers and researchers who work together to solve problems in audio, vision, and language with AI.
-=== <span id="Hugging Face's Open-source Library"></span>Hugging Face's Open-source Library ===
+== <span id="Hugging Face's Open-source Library"></span>Hugging Face's Open-source Library ==
 Hugging Face's open-source library, Transformers, is widely used for natural language processing tasks. The company also offers an Inference API that allows developers to serve their models directly from Hugging Face infrastructure and run large scale NLP models in milliseconds with just a few lines of code. Hugging Face offers a wide range of machine learning models and datasets, as well as tools for building, training, and deploying state-of-the-art models.
-=== <span id="Private Hub"></span>Private Hub ===
+== <span id="Private Hub"></span>Private Hub ==
 * [https://huggingface.co/platform Private Hub]
 ** [https://huggingface.co/docs/hub/main Hugging Face Hub documentation]
-=== <span id="LightGPT"></span>LightGPT ===
+== <span id="LightGPT"></span>LightGPT ==
 * [https://huggingface.co/amazon/LightGPT amazon/LightGPT]
 * [https://huggingface.co/amazon/LightGPT/blob/main/README.md  README.md · amazon/LightGPT]
@@ Line 56: / Line 56: @@
 GPT-J 6B is a transformer model trained using Ben Wang's Mesh Transformer JAX. "GPT-J" refers to the class of model, while "6B" represents the number of trainable parameters. The model consists of 28 layers with a model dimension of 4096, and a feedforward dimension of 16384. The model dimension is split into 16 heads, each with a dimension of 256. Rotary Position Embedding (RoPE) is applied to 64 dimensions of each head. The model is trained with a tokenization vocabulary of 50257, using the same set of BPEs as GPT-2/GPT-3. GPT-J learns an inner representation of the English language that can be used to extract features useful for downstream tasks. The model is best at what it was pretrained for however, which is generating text from a prompt. GPT-J-6B is not intended for deployment without fine-tuning, supervision, and/or moderation. It is not a product in itself and cannot be used for human-facing interactions. For example, the model may generate harmful or offensive text. Please evaluate the risks associated with your particular use case.
-=== <span id="Whisper"></span>Whisper ===
+== <span id="Whisper"></span>Whisper ==
 <youtube>8xYYvO7LGBw</youtube>