Compare Models
-
Google
BERT
FREEBERT (Bidirectional Encoder Representations from Transformers) was introduced in 2018 by researchers at Google AI. BERT uses AI in the form of natural language processing (NLP), natural language understanding (NLU), and sentiment analysis to process every word in a search query in relation to all the other words in a sentence, giving it a robust understanding of context and semantics. This pre-training process is incredibly powerful and the learned weights can be fine-tuned with just one additional output layer to create models for a variety of NLP tasks such as question answering and sentiment analysis. You can download the smaller BERT models for FREE from the official BERT GitHub page. -
BigScience
BLOOM
FREEBigScience Large Open-science Open-access Multilingual Language Model (BLOOM) is a transformer-based LLM. Over 1,000 AI researchers created it to provide a free large language model for everyone who wants to try and it is a multilingual LLM. BLOOM is an autoregressive Large Language Model (LLM), trained to continue text from a prompt on vast amounts of text data using industrial-scale computational resources. It can output coherent text in 46 languages and 13 programming languages. It is free, and everybody who wants to can try it out. To interact with the API, you’ll need to request a token. This is done with a post request to the server. Tokens are only valid for two weeks. After which, a new one must be generated. Trained on around 176B parameters, it is considered an alternative to OpenAI models. There is a downloadable model, and a hosted API is available. -
Databricks
Dolly 2.0
FREEDolly 2.0 by Databricks, is the first open source, instruction-following Large Language Model, fine-tuned on a human-generated instruction dataset and is licensed for research and commercial use, which means any organization can create, own, and customize powerful LLMs that can talk to people without paying for API access or sharing data with third parties.Dolly 2.0 is a 12B parameter language model based on the EleutherAI pythia model family and fine-tuned exclusively on a new, high-quality human generated instruction following dataset (crowdsourced among Databricks employees – so cool). Dolly-v2-12b is not a state-of-the-art model, but it does exhibit surprisingly high-quality instruction following behavior not characteristic of the foundation model on which it is based. Dolly v2 is also available in smaller model sizes: dolly-v2-7b, a 6.9 billion parameter based on pythia-6.9b and dolly-v2-3b, a 2.8 billion parameter based on pythia-2.8b.Dolly 2.0 can be used for brainstorming, classification, open Q&A, closed Q&A, content generation, information extraction, and summarization. You can access the Dolly 2.0 can training code, the dataset, and the model weights on Hugging Face. -
Google, Stanford University
Electra
FREEELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately) is a transformer-based model like BERT, but it uses a different pre-training approach, which is more efficient and requires less computational resources. It was created by a team of researchers from Google Research, Brain Team, and Stanford University. ELECTRA models are trained to distinguish “real” input tokens vs “fake” input tokens generated by another neural network (for the more technical audience, ELECTRA uses a new pre-training task, called replaced token detection (RTD), that trains a bidirectional model while learning from all input positions). Inspired by generative adversarial networks (GANs), ELECTRA trains the model to distinguish between “real” and “fake” input data. At small scale, ELECTRA achieves strong results even when trained on a single GPU. At large scale, ELECTRA achieves state-of-the-art results on the SQuAD 2.0 dataset. Go to GitHub where you can access the three models (ELECTRA-Small, ELECTRA-Base and ELECTRA-Large). -
Google
FLAN-T5
FREEIf you already know T5, FLAN-T5 is just better at everything. For the same number of parameters, these models have been fine-tuned on more than 1,000 additional tasks covering more languages – the NLP is for English, German, French. It has Apache-2.0 license which is a permissive open source license that allows for commercial use. With appropriate prompting, it can perform zero-shot NLP tasks such as text summarization, common sense reasoning, natural language inference, question answering, sentence and sentiment classification, translation, and pronoun resolution. -
Google
Flan-UL2
FREEDeveloped by Google, Flan-UL2, which is a more powerful version of the T5 model that has been trained using Flan, and it is downloadable from Hugging Face. It shows performance exceeding the ‘prior’ versions of Flan-T5. With the ability to reason for itself and generalize better than the previous models, Flan-UL2 is a great improvement. Flan-UL2 is a machine learning model that can generate textual descriptions of images and has the potential to be used for image search, video captioning, automated content generation, and visual question answering. Flan-UL2 has an Apache-2.0 license, which is a permissive open source license that allows for commercial use.If Flan-UL2’s 20B parameters are too much, consider the previous iteration of Flan-T5, which comes in five different sizes and might be more suitable for your needs. -
EleutherAI
GPT-J
FREEEleutherAI is a leading non-profit research institute focused on large-scale artificial intelligence research. EleutherAI has trained and released several LLMs and the codebases used to train them. GPT-J can be used for code generation, making a chat bot, story writing, language translation and searching. 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, which is generating text from a prompt. EleutherAI has a web page where you can test to see how the GPT-J works, or you can run GPT-J on google colab, or use the Hugging Face Transformers library. -
EleutherAI
GPT-NeoX-20B
FREEEleutherAI has trained and released several LLMs and the codebases used to train them. EleutherAI is a leading non-profit research institute focused on large-scale artificial intelligence research. GPT-NeoX-20B is a 20 billion parameter autoregressive language model trained on the Pile using the GPT-NeoX library. Its architecture intentionally resembles that of GPT-3, and is almost identical to that of GPT-J- 6B. Its training dataset contains a multitude of English-language texts, reflecting the general-purpose nature of this model. It is a transformer-based language model and is English-language only, and thus cannot be used for translation or generating text in other languages. It is freely and openly available to the public through a permissive license. -
Microsoft
VALL-E
OTHERVALL-E is a LLM for text to speech synthesis (TTS) developed by Microsoft (technically it is a neural codec language model). Its creators state that VALL-E could be used for high-quality text-to-speech applications, speech editing where a recording of a person could be edited and changed from a text transcript (making them say something they originally didn’t), and audio content creation when combined with other generative AI models. Studies indicate that VALL-E notably surpasses the leading zero-shot TTS system regarding speech authenticity and resemblance to the speaker. Furthermore, it has been observed that VALL-E is capable of retaining the emotional expression and ambient acoustics of the speaker within the synthesized output. Unfortunately, VALL-E is not available for any form of public consumption at this time. At the time of writing, VALL-E is a research project, and there is no customer onboarding queue or waitlist (but you can apply to be part of the first testers group). -
LMSYS Org
Vicuna-13B
FREEVicuna-13B is an open-source chatbot developed by a team of researchers from UC Berkeley, CMU, Stanford, MBZUAI, and UC San Diego. The chatbot was trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT. There is a 13B and 7B parameter models that are available on Hugging Face.
Vicuna-13B achieves more than 90% quality of OpenAI ChatGPT and Google Bard while outperforming other models like LLaMA and Stanford Alpaca in more than 90% of cases. The code and weights and an online demo are publicly available for non-commercial use. Here is a link to learn more about how it compares to other models – https://lmsys.org/blog/2023-03-30-vicuna/.
To use this model, you need to install LLaMA weights first and convert them into Hugging Face weights, and the cost of training Vicuna-13B is around $300.
-
Yandex
YaLM
FREEYaLM 100B is a GPT-like neural network for generating and processing text. It can be used freely by developers and researchers from all over the world. It took 65 days to train the model on a cluster of 800 A100 graphics cards and 1.7 TB of online texts, books, and countless other sources in both English and Russian. Researchers and developers can use the corporate-size solution to solve the most complex problems associated with natural language processing.Training details and best practices on acceleration and stabilizations can be found on Medium (English) and Habr (Russian) articles. The model is published under the Apache 2.0 license that permits both research and commercial use.
