Difference between revisions of "Large Language Model (LLM)"
m |
m |
||
| Line 25: | Line 25: | ||
** [https://www.deepmind.com/blog/language-modelling-at-scale-gopher-ethical-considerations-and-retrieval Gopher |] [[Google | DeepMind]] | ** [https://www.deepmind.com/blog/language-modelling-at-scale-gopher-ethical-considerations-and-retrieval Gopher |] [[Google | DeepMind]] | ||
** [https://www.infoq.com/news/2019/11/microsoft-ai-conversation/ DialogGPT] ...Microsoft Releases DialogGPT AI Conversation Model | Anthony Alford - InfoQ - trained on over 147M dialogs | ** [https://www.infoq.com/news/2019/11/microsoft-ai-conversation/ DialogGPT] ...Microsoft Releases DialogGPT AI Conversation Model | Anthony Alford - InfoQ - trained on over 147M dialogs | ||
| − | |||
** [https://github.com/THUDM/GLM-130B GLM-130B] ... Open Bilingual Pre-Trained Model | ** [https://github.com/THUDM/GLM-130B GLM-130B] ... Open Bilingual Pre-Trained Model | ||
** [https://www.reuters.com/technology/facebook-owner-meta-opens-access-ai-large-language-model-2022-05-03/ OPT-175B]...[[Meta|Facebook]]-owner Meta opens access to AI large language model | Elizabeth Culliford - Reuters ... [[Meta|Facebook]] 175-billion-parameter language model - Open Pretrained Transformer | ** [https://www.reuters.com/technology/facebook-owner-meta-opens-access-ai-large-language-model-2022-05-03/ OPT-175B]...[[Meta|Facebook]]-owner Meta opens access to AI large language model | Elizabeth Culliford - Reuters ... [[Meta|Facebook]] 175-billion-parameter language model - Open Pretrained Transformer | ||
| Line 38: | Line 37: | ||
** [https://github.com/allenai/macaw Macaw | AI2] | ** [https://github.com/allenai/macaw Macaw | AI2] | ||
** [https://arxiv.org/pdf/2212.13138.pdf Med-PaLM] ... aligned to the medical domain | ** [https://arxiv.org/pdf/2212.13138.pdf Med-PaLM] ... aligned to the medical domain | ||
| − | ** [https:// | + | ** [https://github.com/karpathy/minGPT minGPT | Andrej Karpathy - GitHub] |
** [https://developer.nvidia.com/blog/using-deepspeed-and-megatron-to-train-megatron-turing-nlg-530b-the-worlds-largest-and-most-powerful-generative-language-model/ Megatron NLG] ... Monolithic Transformer Language NLP Model Triple the Size of [[OpenAI]]’s GPT-3 | ** [https://developer.nvidia.com/blog/using-deepspeed-and-megatron-to-train-megatron-turing-nlg-530b-the-worlds-largest-and-most-powerful-generative-language-model/ Megatron NLG] ... Monolithic Transformer Language NLP Model Triple the Size of [[OpenAI]]’s GPT-3 | ||
** [https://muse.lighton.ai/home Muse] ... VLM-4, a set of natively trained large Language Models in French, Italian, Spanish, German, and English | ** [https://muse.lighton.ai/home Muse] ... VLM-4, a set of natively trained large Language Models in French, Italian, Spanish, German, and English | ||
| Line 52: | Line 51: | ||
** [https://ai.facebook.com/blog/textless-nlp-generating-expressive-speech-from-raw-audio/ Textless NLP ... Generating expressive speech from raw audio] | ** [https://ai.facebook.com/blog/textless-nlp-generating-expressive-speech-from-raw-audio/ Textless NLP ... Generating expressive speech from raw audio] | ||
** [[Toolformer]] | [[Meta]] ... models can teach themselves to use tools and APIs | ** [[Toolformer]] | [[Meta]] ... models can teach themselves to use tools and APIs | ||
| + | ** [https://turing.microsoft.com/ Turing-NLG |] [[Microsoft]] | ||
** [https://github.com/allenai/unifiedqa UnifiedQA] ... single QA system | ** [https://github.com/allenai/unifiedqa UnifiedQA] ... single QA system | ||
** [https://openai.com/blog/webgpt/ WebGPT] ... GPT-3 version that can search the web | ** [https://openai.com/blog/webgpt/ WebGPT] ... GPT-3 version that can search the web | ||
Revision as of 00:03, 25 February 2023
YouTube search... ...Google search
- Models:
- Alpa ... serving large models like GPT-3 simple, affordable, accessible
- BioGPT ... Microsoft language model trained for biomedical tasks
- BLOOM ... Big Science Language Open-science Open-access Multilingual ... 176B
- Cedille ... open-source French language model
- ChatGPT | OpenAI
- Chinchilla | DeepMind
- ctrl ... a Conditional Transformer Language Model for Controllable Generation | Salesforce
- Dataflow-as-a-Service | SambaNova
- Gopher | DeepMind
- DialogGPT ...Microsoft Releases DialogGPT AI Conversation Model | Anthony Alford - InfoQ - trained on over 147M dialogs
- GLM-130B ... Open Bilingual Pre-Trained Model
- OPT-175B...Facebook-owner Meta opens access to AI large language model | Elizabeth Culliford - Reuters ... Facebook 175-billion-parameter language model - Open Pretrained Transformer
- Bidirectional Encoder Representations from Transformers (BERT)
- GLaM | Google
- GShard | Google ... Scaling Giant Models with Conditional Computation and Automatic Sharding
- GPT-2 | OpenAI ... Generative Pre-trained Transformer 2 by OpenAI
- GPT-Neo ... Open-source GPT-3 by EleutherAI
- InstructGPT ... OpenAI 1.3B InstructGPT model over outputs from a 175B GPT-3 model
- Jurassic-1 Language Model ... huge 178B language model to rival OpenAI's GPT-3]
- LaMDA | Google ... experimental language model
- Macaw | AI2
- Med-PaLM ... aligned to the medical domain
- minGPT | Andrej Karpathy - GitHub
- Megatron NLG ... Monolithic Transformer Language NLP Model Triple the Size of OpenAI’s GPT-3
- Muse ... VLM-4, a set of natively trained large Language Models in French, Italian, Spanish, German, and English
- nanoGPT ... for training/finetuning medium-sized GPTs
- Codex | OpenAI ... translates natural language into code
- OpenGPT-X ... model for Europe
- Palmyra | Hugging Face ... a privacy-first LLM for enterprises
- Pathways Language Model (PaLM) ...scaling to 540 Billion Parameters
- PLATO-XL | Baidu ... 11B Parameter Chatbot
- RETRO | DeepMind
- [https://arxiv.org/abs/2101.03961 Switch Transformers | Google Brain ... trillion parameters
- T0pp | Hugging Face
- Textless NLP ... Generating expressive speech from raw audio
- Toolformer | Meta ... models can teach themselves to use tools and APIs
- Turing-NLG | Microsoft
- UnifiedQA ... single QA system
- WebGPT ... GPT-3 version that can search the web
- Wu Dao 1.0 (Enlightment 1.0) ... China’s first homegrown super-scale intelligent model
- YaLM 100B ... Yandex YaLM 100B parameters
- Yuan 1.0 | Inspur ... 245B parameters
- OpenAI Blog | OpenAI
- Attention Mechanism/Transformer Model
- Generative Pre-trained Transformer (GPT)
- SambaNova Systems ... Dataflow-as-a-Service GPT
