diff --git a/.github/ISSUE_TEMPLATE/maintainers-release.md b/.github/ISSUE_TEMPLATE/maintainers-release.md index a652e429f1..3b7a9959ba 100644 --- a/.github/ISSUE_TEMPLATE/maintainers-release.md +++ b/.github/ISSUE_TEMPLATE/maintainers-release.md @@ -65,7 +65,11 @@ I need the following from you: ### GitHub release -Now paste the former release (or 1.5.0 which was accurate and great), including the new contributors and +```markdown +Please create the 1.2.3 Release Notes for GitHub. The following were the Release Notes for 1.1.0. Use a truthful and honest tone, undestanding that people's time and attention span is short. Today is 2023-12-20. +``` + +Now paste-attachment the former release notes (or 1.5.0 which was accurate and great), including the new contributors and some stats (# of commits, etc.), and roll it for the new release. ### Discord announcement diff --git a/README.md b/README.md index 42d736a852..7c18cdf867 100644 --- a/README.md +++ b/README.md @@ -21,7 +21,19 @@ shows the current developments and future ideas. - Got a suggestion? [_Add your roadmap ideas_](https://github.com/enricoros/big-agi/issues/new?&template=roadmap-request.md) - Want to contribute? [_Pick up a task!_](https://github.com/users/enricoros/projects/4/views/4) - _easy_ to _pro_ -### What's New in 1.7.3 · Dec 13, 2023 · Attachment Theory 🌟 +### What's New in 1.8.0 · Dec 20, 2023 · To The Moon And Back · 🚀🌕🔙 + +- **Google Gemini Support**: Use the newest Google models. [#275](https://github.com/enricoros/big-agi/issues/275) +- **Mistral Platform**: Mixtral and future models support. [#273](https://github.com/enricoros/big-agi/issues/273) +- **Diagram Instructions**. Thanks to @joriskalz! [#280](https://github.com/enricoros/big-agi/pull/280) +- Ollama Chats: Enhanced chatting experience. [#270](https://github.com/enricoros/big-agi/issues/270) +- Mac Shortcuts Fix: Improved UX on Mac +- **Single-Tab Mode**: Data integrity with single window. [#268](https://github.com/enricoros/big-agi/issues/268) +- **Updated Models**: Latest Ollama (v0.1.17) and OpenRouter models +- Official Downloads: Easy access to the latest big-AGI on [big-AGI.com](https://big-agi.com) +- For developers: [troubleshot networking](https://github.com/enricoros/big-AGI/issues/276#issuecomment-1858591483), fixed Vercel deployment, cleaned up the LLMs/Streaming framework + +### What's New in 1.7.0 · Dec 11, 2023 - **Attachments System Overhaul**: Drag, paste, link, snap, text, images, PDFs and more. [#251](https://github.com/enricoros/big-agi/issues/251) - **Desktop Webcam Capture**: Image capture now available as Labs feature. [#253](https://github.com/enricoros/big-agi/issues/253) @@ -31,9 +43,6 @@ shows the current developments and future ideas. - Optimized Voice Input and Performance - Latest Ollama and Oobabooga models - For developers: **Password Protection**: HTTP Basic Auth. [Learn How](https://github.com/enricoros/big-agi/blob/main/docs/deploy-authentication.md) -- [1.7.1]: Improved Ollama chats. [#270](https://github.com/enricoros/big-agi/issues/270) -- [1.7.2]: OpenRouter login & free models 🎁 -- [1.7.3]: Mistral Platform support. [#273](https://github.com/enricoros/big-agi/issues/273) ### What's New in 1.6.0 - Nov 28, 2023 diff --git a/docs/changelog.md b/docs/changelog.md index 556318aef1..ae2acd3384 100644 --- a/docs/changelog.md +++ b/docs/changelog.md @@ -5,12 +5,24 @@ by release. - For the live roadmap, please see [the GitHub project](https://github.com/users/enricoros/projects/4/views/2) -### 1.8.0 - Dec 2023 +### 1.9.0 - Dec 2023 - work in progress: [big-AGI open roadmap](https://github.com/users/enricoros/projects/4/views/2), [help here](https://github.com/users/enricoros/projects/4/views/4) -- milestone: [1.8.0](https://github.com/enricoros/big-agi/milestone/8) +- milestone: [1.9.0](https://github.com/enricoros/big-agi/milestone/9) -### What's New in 1.7.3 · Dec 13, 2023 · Attachment Theory 🌟 +### What's New in 1.8.0 · Dec 20, 2023 · To The Moon And Back · 🚀🌕🔙 + +- **Google Gemini Support**: Use the newest Google models. [#275](https://github.com/enricoros/big-agi/issues/275) +- **Mistral Platform**: Mixtral and future models support. [#273](https://github.com/enricoros/big-agi/issues/273) +- **Diagram Instructions**. Thanks to @joriskalz! [#280](https://github.com/enricoros/big-agi/pull/280) +- Ollama Chats: Enhanced chatting experience. [#270](https://github.com/enricoros/big-agi/issues/270) +- Mac Shortcuts Fix: Improved UX on Mac +- **Single-Tab Mode**: Data integrity with single window. [#268](https://github.com/enricoros/big-agi/issues/268) +- **Updated Models**: Latest Ollama (v0.1.17) and OpenRouter models +- Official Downloads: Easy access to the latest big-AGI on [big-AGI.com](https://big-agi.com) +- For developers: [troubleshot networking](https://github.com/enricoros/big-AGI/issues/276#issuecomment-1858591483), fixed Vercel deployment, cleaned up the LLMs/Streaming framework + +### What's New in 1.7.0 · Dec 11, 2023 · Attachment Theory - **Attachments System Overhaul**: Drag, paste, link, snap, text, images, PDFs and more. [#251](https://github.com/enricoros/big-agi/issues/251) - **Desktop Webcam Capture**: Image capture now available as Labs feature. [#253](https://github.com/enricoros/big-agi/issues/253) @@ -20,9 +32,6 @@ by release. - Optimized Voice Input and Performance - Latest Ollama and Oobabooga models - For developers: **Password Protection**: HTTP Basic Auth. [Learn How](https://github.com/enricoros/big-agi/blob/main/docs/deploy-authentication.md) -- [1.7.1]: Improved Ollama chats. [#270](https://github.com/enricoros/big-agi/issues/270) -- [1.7.2]: OpenRouter login & free models 🎁 -- [1.7.3]: Mistral Platform support. [#273](https://github.com/enricoros/big-agi/issues/273) ### What's New in 1.6.0 - Nov 28, 2023 · Surf's Up diff --git a/package-lock.json b/package-lock.json index b0f9cf5934..aa488b5649 100644 --- a/package-lock.json +++ b/package-lock.json @@ -1,12 +1,12 @@ { "name": "big-agi", - "version": "1.7.3", + "version": "1.8.0", "lockfileVersion": 3, "requires": true, "packages": { "": { "name": "big-agi", - "version": "1.7.3", + "version": "1.8.0", "hasInstallScript": true, "dependencies": { "@dqbd/tiktoken": "^1.0.7", diff --git a/package.json b/package.json index 01040b853b..a68a319bdc 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "big-agi", - "version": "1.7.3", + "version": "1.8.0", "private": true, "scripts": { "dev": "next dev", diff --git a/src/apps/news/AppNews.tsx b/src/apps/news/AppNews.tsx index e5f1d6e5a7..4043bf4b21 100644 --- a/src/apps/news/AppNews.tsx +++ b/src/apps/news/AppNews.tsx @@ -84,8 +84,8 @@ export function AppNews() { const addPadding = false; //!firstCard; // || showExpander; return - - + + {ni.text ? ni.text : ni.versionName ? `${ni.versionCode} · ${ni.versionName}` : `Version ${ni.versionCode}:`} diff --git a/src/apps/news/news.data.tsx b/src/apps/news/news.data.tsx index 935225fd12..5356f53fee 100644 --- a/src/apps/news/news.data.tsx +++ b/src/apps/news/news.data.tsx @@ -10,10 +10,10 @@ import { platformAwareKeystrokes } from '~/common/components/KeyStroke'; // update this variable every time you want to broadcast a new version to clients -export const incrementalVersion: number = 8; +export const incrementalVersion: number = 9; const B = (props: { href?: string, children: React.ReactNode }) => { - const boldText = {props.children}; + const boldText = {props.children}; return props.href ? {boldText} : boldText; @@ -27,11 +27,12 @@ const RIssues = `${OpenRepo}/issues`; export const newsCallout = - + Open Roadmap - - The roadmap is officially out. For the first time you get a look at what's brewing, up and coming, and get a chance to pick up cool features! + + Take a peek at our roadmap to see what's in the pipeline. + Discover upcoming features and let us know what excites you the most! @@ -39,7 +40,7 @@ export const newsCallout = fullWidth variant='soft' color='primary' endDecorator={} component={Link} href={OpenProject} noLinkStyle target='_blank' > - Explore the Roadmap + Explore @@ -67,10 +68,27 @@ export const NewsItems: NewsItem[] = [ ], },*/ { - versionCode: '1.7.3', + versionCode: '1.8.0', + versionName: 'To The Moon And Back', + versionMoji: '🚀🌕🔙❤️', + versionDate: new Date('2023-12-20T09:30:00Z'), + items: [ + { text: <>Google Gemini models support }, + { text: <>Mistral Platform support }, + { text: <>Ollama chats perfection }, + { text: <>Custom diagrams instructions (@joriskalz) }, + { text: <>Single-Tab mode, enhances data integrity and prevents DB corruption }, + { text: <>Updated Ollama (v0.1.17) and OpenRouter models }, + { text: <>More: fixed ⌘ shortcuts on Mac }, + { text: <>Website: official downloads }, + { text: <>Easier Vercel deployment, documented network troubleshooting, dev: true }, + ], + }, + { + versionCode: '1.7.0', versionName: 'Attachment Theory', - versionDate: new Date('2023-12-11T06:00:00Z'), // new Date().toISOString() - // versionDate: new Date('2023-12-10T12:00:00Z'), // 1.7.0 + // versionDate: new Date('2023-12-11T06:00:00Z'), // 1.7.3 + versionDate: new Date('2023-12-10T12:00:00Z'), // 1.7.0 items: [ { text: <>Redesigned attachments system: drag, paste, link, snap, images, text, pdfs }, { text: <>Desktop webcam access for direct image capture (Labs option) }, @@ -80,9 +98,6 @@ export const NewsItems: NewsItem[] = [ { text: <>{platformAwareKeystrokes('Ctrl+Shift+O')}: quick access to model options }, { text: <>Optimized voice input and performance }, { text: <>Latest Ollama and Oobabooga models }, - { text: <>1.7.1: Improved Ollama chats }, - { text: <>1.7.2: Updated OpenRouter models 🎁 }, - { text: <>1.7.3: Mistral Platform support }, ], }, { @@ -162,6 +177,7 @@ export const NewsItems: NewsItem[] = [ interface NewsItem { versionCode: string; versionName?: string; + versionMoji?: string; versionDate?: Date; text?: string | React.JSX.Element; items?: { diff --git a/src/modules/llms/server/ollama/ollama.models.ts b/src/modules/llms/server/ollama/ollama.models.ts index b32a1f7012..d52d0e6e49 100644 --- a/src/modules/llms/server/ollama/ollama.models.ts +++ b/src/modules/llms/server/ollama/ollama.models.ts @@ -6,59 +6,59 @@ * from: https://ollama.ai/library?sort=featured */ export const OLLAMA_BASE_MODELS: { [key: string]: { description: string, pulls: number, added?: string } } = { - 'llama2': { description: 'The most popular model for general use.', pulls: 152400 }, - 'mistral': { description: 'The 7B model released by Mistral AI, updated to version 0.2', pulls: 80700 }, - 'llava': { description: '🌋 A novel end-to-end trained large multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language understanding.', pulls: 1430, added: "20231215" }, - 'mixtral': { description: 'A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI.', pulls: 2560, added: "20231215" }, - 'starling-lm': { description: 'Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness.', pulls: 3181, added: '20231129' }, - 'neural-chat': { description: 'A fine-tuned model based on Mistral with good coverage of domain and language.', pulls: 4107, added: '20231129' }, - 'codellama': { description: 'A large language model that can use text prompts to generate and discuss code.', pulls: 75800 }, - 'llama2-uncensored': { description: 'Uncensored Llama 2 model by George Sung and Jarrad Hope.', pulls: 32900 }, - 'dolphin-mixtral': { description: 'An uncensored, fine-tuned model based on the Mixtral mixture of experts model that excels at coding tasks. Created by Eric Hartford.', pulls: 30000, added: "20231215" }, - 'orca-mini': { description: 'A general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware.', pulls: 28200 }, - 'vicuna': { description: 'General use chat model based on Llama and Llama 2 with 2K to 16K context sizes.', pulls: 22200 }, - 'wizard-vicuna-uncensored': { description: 'Wizard Vicuna Uncensored is a 7B, 13B, and 30B parameter model based on Llama 2 uncensored by Eric Hartford.', pulls: 14300 }, - 'phind-codellama': { description: 'Code generation model based on CodeLlama.', pulls: 11000 }, - 'zephyr': { description: 'Zephyr beta is a fine-tuned 7B version of mistral that was trained on on a mix of publicly available, synthetic datasets.', pulls: 10900 }, - 'wizardcoder': { description: 'Llama based code generation model focused on Python.', pulls: 10400 }, - 'mistral-openorca': { description: 'Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset.', pulls: 9617 }, - 'nous-hermes': { description: 'General use models based on Llama and Llama 2 from Nous Research.', pulls: 8933 }, - 'deepseek-coder': { description: 'DeepSeek Coder is trained from scratch on both 87% code and 13% natural language in English and Chinese. Each of the models are pre-trained on 2 trillion tokens.', pulls: 8664, added: '20231129' }, - 'wizard-math': { description: 'Model focused on math and logic problems', pulls: 8029 }, - 'llama2-chinese': { description: 'Llama 2 based model fine tuned to improve Chinese dialogue ability.', pulls: 7760 }, - 'falcon': { description: 'A large language model built by the Technology Innovation Institute (TII) for use in summarization, text generation, and chat bots.', pulls: 7024 }, - 'orca2': { description: 'Orca 2 is built by Microsoft research, and are a fine-tuned version of Meta\'s Llama 2 models. The model is designed to excel particularly in reasoning.', pulls: 6628, added: '20231129' }, - 'stable-beluga': { description: 'Llama 2 based model fine tuned on an Orca-style dataset. Originally called Free Willy.', pulls: 6398 }, - 'codeup': { description: 'Great code generation model based on Llama2.', pulls: 6216 }, - 'everythinglm': { description: 'Uncensored Llama2 based model with 16k context size.', pulls: 5193 }, - 'medllama2': { description: 'Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset.', pulls: 4850 }, - 'wizardlm-uncensored': { description: 'Uncensored version of Wizard LM model.', pulls: 4705 }, - 'starcoder': { description: 'StarCoder is a code generation model trained on 80+ programming languages.', pulls: 4093 }, - 'dolphin2.2-mistral': { description: 'An instruct-tuned model based on Mistral. Version 2.2 is fine-tuned for improved conversation and empathy.', pulls: 4037 }, - 'openchat': { description: 'A family of open-source models trained on a wide variety of data, surpassing ChatGPT on various benchmarks.', pulls: 3837, added: '20231129' }, - 'wizard-vicuna': { description: 'Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj.', pulls: 3583 }, - 'openhermes2.5-mistral': { description: 'OpenHermes 2.5 Mistral 7B is a Mistral 7B fine-tune, a continuation of OpenHermes 2 model, which trained on additional code datasets.', pulls: 3475 }, - 'open-orca-platypus2': { description: 'Merge of the Open Orca OpenChat model and the Garage-bAInd Platypus 2 model. Designed for chat and code generation.', pulls: 3192 }, - 'yi': { description: 'A high-performing, bilingual base model.', pulls: 3098 }, - 'yarn-mistral': { description: 'An extension of Mistral to support a context of up to 128k tokens.', pulls: 2955 }, - 'samantha-mistral': { description: 'A companion assistant trained in philosophy, psychology, and personal relationships. Based on Mistral.', pulls: 2366 }, - 'sqlcoder': { description: 'SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks', pulls: 2195 }, - 'yarn-llama2': { description: 'An extension of Llama 2 that supports a context of up to 128k tokens.', pulls: 2076 }, - 'meditron': { description: 'Open-source medical large language model adapted from Llama 2 to the medical domain.', pulls: 2008, added: '20231129' }, - 'openhermes2-mistral': { description: 'OpenHermes 2 Mistral is a 7B model fine-tuned on Mistral with 900,000 entries of primarily GPT-4 generated data from open datasets.', pulls: 1740 }, - 'stablelm-zephyr': { description: 'A lightweight chat model allowing accurate, and responsive output without requiring high-end hardware.', pulls: 1689, added: '20231210' }, - 'deepseek-llm': { description: 'An advanced language model crafted with 2 trillion bilingual tokens.', pulls: 1615, added: '20231129' }, - 'mistrallite': { description: 'MistralLite is a fine-tuned model based on Mistral with enhanced capabilities of processing long contexts.', pulls: 1456 }, - 'wizardlm': { description: 'General use 70 billion parameter model based on Llama 2.', pulls: 1404 }, - 'dolphin2.1-mistral': { description: 'An instruct-tuned model based on Mistral and trained on a dataset filtered to remove alignment and bias.', pulls: 1391 }, - 'codebooga': { description: 'A high-performing code instruct model created by merging two existing code models.', pulls: 1371 }, - 'magicoder': { description: '🎩 Magicoder is a family of 7B parameter models trained on 75K synthetic instruction data using OSS-Instruct, a novel approach to enlightening LLMs with open-source code snippets.', pulls: 1245, added: '20231210' }, - 'goliath': { description: 'A language model created by combining two fine-tuned Llama 2 70B models into one.', pulls: 1070, added: '20231129' }, - 'nexusraven': { description: 'Nexus Raven is a 13B instruction tuned model for function calling tasks.', pulls: 971 }, - 'alfred': { description: 'A robust conversational model designed to be used for both chat and instruct use cases.', pulls: 851, added: '20231129' }, - 'xwinlm': { description: 'Conversational model based on Llama 2 that performs competitively on various benchmarks.', pulls: 825 }, - 'bakllava': { description: 'BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture.', pulls: 647, added: "20231215" }, + 'llama2': { description: 'The most popular model for general use.', pulls: 165600 }, + 'mistral': { description: 'The 7B model released by Mistral AI, updated to version 0.2', pulls: 92200 }, + 'llava': { description: '🌋 A novel end-to-end trained large multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language understanding.', pulls: 3563, added: '20231215' }, + 'mixtral': { description: 'A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI.', pulls: 8277, added: '20231215' }, + 'starling-lm': { description: 'Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness.', pulls: 3657, added: '20231129' }, + 'neural-chat': { description: 'A fine-tuned model based on Mistral with good coverage of domain and language.', pulls: 4647, added: '20231129' }, + 'codellama': { description: 'A large language model that can use text prompts to generate and discuss code.', pulls: 79800 }, + 'dolphin-mixtral': { description: 'An uncensored, fine-tuned model based on the Mixtral mixture of experts model that excels at coding tasks. Created by Eric Hartford.', pulls: 48400, added: '20231215' }, + 'llama2-uncensored': { description: 'Uncensored Llama 2 model by George Sung and Jarrad Hope.', pulls: 36600 }, + 'orca-mini': { description: 'A general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware.', pulls: 30000 }, + 'vicuna': { description: 'General use chat model based on Llama and Llama 2 with 2K to 16K context sizes.', pulls: 22700 }, + 'wizard-vicuna-uncensored': { description: 'Wizard Vicuna Uncensored is a 7B, 13B, and 30B parameter model based on Llama 2 uncensored by Eric Hartford.', pulls: 15300 }, + 'zephyr': { description: 'Zephyr beta is a fine-tuned 7B version of mistral that was trained on on a mix of publicly available, synthetic datasets.', pulls: 11500 }, + 'phind-codellama': { description: 'Code generation model based on CodeLlama.', pulls: 11200 }, + 'wizardcoder': { description: 'Llama based code generation model focused on Python.', pulls: 10700 }, + 'deepseek-coder': { description: 'DeepSeek Coder is trained from scratch on both 87% code and 13% natural language in English and Chinese. Each of the models are pre-trained on 2 trillion tokens.', pulls: 10200 }, + 'mistral-openorca': { description: 'Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset.', pulls: 9842 }, + 'nous-hermes': { description: 'General use models based on Llama and Llama 2 from Nous Research.', pulls: 9071 }, + 'wizard-math': { description: 'Model focused on math and logic problems', pulls: 8328 }, + 'llama2-chinese': { description: 'Llama 2 based model fine tuned to improve Chinese dialogue ability.', pulls: 8111 }, + 'orca2': { description: 'Orca 2 is built by Microsoft research, and are a fine-tuned version of Meta\'s Llama 2 models. The model is designed to excel particularly in reasoning.', pulls: 7492, added: '20231129' }, + 'falcon': { description: 'A large language model built by the Technology Innovation Institute (TII) for use in summarization, text generation, and chat bots.', pulls: 7468 }, + 'stable-beluga': { description: 'Llama 2 based model fine tuned on an Orca-style dataset. Originally called Free Willy.', pulls: 6468 }, + 'codeup': { description: 'Great code generation model based on Llama2.', pulls: 6397 }, + 'everythinglm': { description: 'Uncensored Llama2 based model with 16k context size.', pulls: 5347 }, + 'medllama2': { description: 'Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset.', pulls: 5034 }, + 'wizardlm-uncensored': { description: 'Uncensored version of Wizard LM model.', pulls: 4874 }, + 'dolphin2.2-mistral': { description: 'An instruct-tuned model based on Mistral. Version 2.2 is fine-tuned for improved conversation and empathy.', pulls: 4686 }, + 'openchat': { description: 'A family of open-source models trained on a wide variety of data, surpassing ChatGPT on various benchmarks. Updated to version 3.5-1210.', pulls: 4496, added: '20231129' }, + 'starcoder': { description: 'StarCoder is a code generation model trained on 80+ programming languages.', pulls: 4331 }, + 'openhermes2.5-mistral': { description: 'OpenHermes 2.5 Mistral 7B is a Mistral 7B fine-tune, a continuation of OpenHermes 2 model, which trained on additional code datasets.', pulls: 3722 }, + 'wizard-vicuna': { description: 'Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj.', pulls: 3668 }, + 'yi': { description: 'A high-performing, bilingual base model.', pulls: 3335 }, + 'open-orca-platypus2': { description: 'Merge of the Open Orca OpenChat model and the Garage-bAInd Platypus 2 model. Designed for chat and code generation.', pulls: 3219 }, + 'yarn-mistral': { description: 'An extension of Mistral to support a context of up to 128k tokens.', pulls: 3087 }, + 'samantha-mistral': { description: 'A companion assistant trained in philosophy, psychology, and personal relationships. Based on Mistral.', pulls: 2518 }, + 'sqlcoder': { description: 'SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks', pulls: 2338 }, + 'meditron': { description: 'Open-source medical large language model adapted from Llama 2 to the medical domain.', pulls: 2216, added: '20231129' }, + 'yarn-llama2': { description: 'An extension of Llama 2 that supports a context of up to 128k tokens.', pulls: 2201 }, + 'stablelm-zephyr': { description: 'A lightweight chat model allowing accurate, and responsive output without requiring high-end hardware.', pulls: 1983, added: '20231210' }, + 'openhermes2-mistral': { description: 'OpenHermes 2 Mistral is a 7B model fine-tuned on Mistral with 900,000 entries of primarily GPT-4 generated data from open datasets.', pulls: 1790 }, + 'deepseek-llm': { description: 'An advanced language model crafted with 2 trillion bilingual tokens.', pulls: 1732, added: '20231129' }, + 'dolphin2.1-mistral': { description: 'An instruct-tuned model based on Mistral and trained on a dataset filtered to remove alignment and bias.', pulls: 1598 }, + 'mistrallite': { description: 'MistralLite is a fine-tuned model based on Mistral with enhanced capabilities of processing long contexts.', pulls: 1534 }, + 'wizardlm': { description: 'General use 70 billion parameter model based on Llama 2.', pulls: 1454 }, + 'codebooga': { description: 'A high-performing code instruct model created by merging two existing code models.', pulls: 1418 }, + 'phi': { description: 'Phi-2: a 2.7B language model by Microsoft Research that demonstrates outstanding reasoning and language understanding capabilities.', pulls: 1304, added: '20231220' }, + 'bakllava': { description: 'BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture.', pulls: 1189, added: '20231215' }, + 'goliath': { description: 'A language model created by combining two fine-tuned Llama 2 70B models into one.', pulls: 1140, added: '20231129' }, + 'nexusraven': { description: 'Nexus Raven is a 13B instruction tuned model for function calling tasks.', pulls: 1060 }, + 'solar': { description: 'A compact, yet powerful 10.7B large language model designed for single-turn conversation.', pulls: 934 }, + 'alfred': { description: 'A robust conversational model designed to be used for both chat and instruct use cases.', pulls: 902, added: '20231129' }, + 'xwinlm': { description: 'Conversational model based on Llama 2 that performs competitively on various benchmarks.', pulls: 868 }, }; -// export const OLLAMA_LAST_UPDATE: string = '20231215'; -export const OLLAMA_PREV_UPDATE: string = '20231210'; -// export const OLLAMA_PREV_UPDATE: string = '20231129'; \ No newline at end of file +// export const OLLAMA_LAST_UPDATE: string = '20231220'; +export const OLLAMA_PREV_UPDATE: string = '20231210'; \ No newline at end of file diff --git a/src/modules/llms/server/openai/models.data.ts b/src/modules/llms/server/openai/models.data.ts index 28dd5e59fa..1e6a889e13 100644 --- a/src/modules/llms/server/openai/models.data.ts +++ b/src/modules/llms/server/openai/models.data.ts @@ -313,16 +313,16 @@ const orModelMap: { [id: string]: { name: string; cw: number; cp?: number; cc?: 'huggingfaceh4/zephyr-7b-beta': { name: 'Hugging Face: Zephyr 7B', cw: 4096, cp: 0, cc: 0, unfilt: true }, 'openchat/openchat-7b': { name: 'OpenChat 3.5', cw: 8192, cp: 0, cc: 0, unfilt: true }, 'gryphe/mythomist-7b': { name: 'MythoMist 7B', cw: 32768, cp: 0, cc: 0, unfilt: true }, - 'openrouter/cinematika-7b': { name: 'Cinematika 7B (alpha)', cw: 32000, cp: 0, cc: 0, unfilt: true }, - 'mistralai/mixtral-8x7b-instruct': { name: 'Mistral: Mixtral 8x7B Instruct (beta)', cw: 32000, cp: 0, cc: 0, unfilt: true }, + 'openrouter/cinematika-7b': { name: 'Cinematika 7B (alpha)', cw: 32768, cp: 0, cc: 0, unfilt: true }, 'rwkv/rwkv-5-world-3b': { name: 'RWKV v5 World 3B (beta)', cw: 10000, cp: 0, cc: 0, unfilt: true }, 'recursal/rwkv-5-3b-ai-town': { name: 'RWKV v5 3B AI Town (beta)', cw: 10000, cp: 0, cc: 0, unfilt: true }, - 'jebcarter/psyfighter-13b': { name: 'Psyfighter 13B', cw: 4096, cp: 0.001, cc: 0.001, unfilt: true }, - 'koboldai/psyfighter-13b-2': { name: 'Psyfighter v2 13B', cw: 4096, cp: 0.001, cc: 0.001, unfilt: true }, + 'jebcarter/psyfighter-13b': { name: 'Psyfighter 13B', cw: 4096, cp: 0.0001, cc: 0.0001, unfilt: true }, + 'koboldai/psyfighter-13b-2': { name: 'Psyfighter v2 13B', cw: 4096, cp: 0.0001, cc: 0.0001, unfilt: true }, 'nousresearch/nous-hermes-llama2-13b': { name: 'Nous: Hermes 13B', cw: 4096, cp: 0.000075, cc: 0.000075, unfilt: true }, 'meta-llama/codellama-34b-instruct': { name: 'Meta: CodeLlama 34B Instruct', cw: 8192, cp: 0.0002, cc: 0.0002, unfilt: true }, 'phind/phind-codellama-34b': { name: 'Phind: CodeLlama 34B v2', cw: 4096, cp: 0.0002, cc: 0.0002, unfilt: true }, 'intel/neural-chat-7b': { name: 'Neural Chat 7B v3.1', cw: 4096, cp: 0.0025, cc: 0.0025, unfilt: true }, + 'mistralai/mixtral-8x7b-instruct': { name: 'Mistral: Mixtral 8x7B Instruct (beta)', cw: 32768, cp: 0.0003, cc: 0.0003, unfilt: true }, 'haotian-liu/llava-13b': { name: 'Llava 13B', cw: 2048, cp: 0.0025, cc: 0.0025, unfilt: true }, 'nousresearch/nous-hermes-2-vision-7b': { name: 'Nous: Hermes 2 Vision 7B (alpha)', cw: 4096, cp: 0.0025, cc: 0.0025, unfilt: true }, 'meta-llama/llama-2-13b-chat': { name: 'Meta: Llama v2 13B Chat', cw: 4096, cp: 0.000156755, cc: 0.000156755, unfilt: true }, @@ -334,10 +334,12 @@ const orModelMap: { [id: string]: { name: string; cw: number; cp?: number; cc?: 'openai/gpt-4-32k': { name: 'OpenAI: GPT-4 32k', cw: 32767, cp: 0.06, cc: 0.12, unfilt: false }, 'openai/gpt-4-vision-preview': { name: 'OpenAI: GPT-4 Vision (preview)', cw: 128000, cp: 0.01, cc: 0.03, unfilt: false }, 'openai/gpt-3.5-turbo-instruct': { name: 'OpenAI: GPT-3.5 Turbo Instruct', cw: 4095, cp: 0.0015, cc: 0.002, unfilt: false }, - 'google/palm-2-chat-bison': { name: 'Google: PaLM 2 Chat', cw: 9216, cp: 0.0005, cc: 0.0005, unfilt: true }, - 'google/palm-2-codechat-bison': { name: 'Google: PaLM 2 Code Chat', cw: 7168, cp: 0.0005, cc: 0.0005, unfilt: true }, - 'google/palm-2-chat-bison-32k': { name: 'Google: PaLM 2 Chat 32k', cw: 32000, cp: 0.0005, cc: 0.0005, unfilt: true }, - 'google/palm-2-codechat-bison-32k': { name: 'Google: PaLM 2 Code Chat 32k', cw: 32000, cp: 0.0005, cc: 0.0005, unfilt: true }, + 'google/palm-2-chat-bison': { name: 'Google: PaLM 2 Chat', cw: 36864, cp: 0.00025, cc: 0.0005, unfilt: true }, + 'google/palm-2-codechat-bison': { name: 'Google: PaLM 2 Code Chat', cw: 28672, cp: 0.00025, cc: 0.0005, unfilt: true }, + 'google/palm-2-chat-bison-32k': { name: 'Google: PaLM 2 Chat 32k', cw: 131072, cp: 0.00025, cc: 0.0005, unfilt: true }, + 'google/palm-2-codechat-bison-32k': { name: 'Google: PaLM 2 Code Chat 32k', cw: 131072, cp: 0.00025, cc: 0.0005, unfilt: true }, + 'google/gemini-pro': { name: 'Google: Gemini Pro (preview)', cw: 131040, cp: 0.00025, cc: 0.0005, unfilt: true }, + 'google/gemini-pro-vision': { name: 'Google: Gemini Pro Vision (preview)', cw: 65536, cp: 0.00025, cc: 0.0005, unfilt: true }, 'perplexity/pplx-70b-online': { name: 'Perplexity: PPLX 70B Online', cw: 4096, cp: 0, cc: 0.0028, unfilt: true }, 'perplexity/pplx-7b-online': { name: 'Perplexity: PPLX 7B Online', cw: 4096, cp: 0, cc: 0.00028, unfilt: true }, 'perplexity/pplx-7b-chat': { name: 'Perplexity: PPLX 7B Chat', cw: 8192, cp: 0.00007, cc: 0.00028, unfilt: true }, @@ -347,7 +349,7 @@ const orModelMap: { [id: string]: { name: string; cw: number; cp?: number; cc?: 'nousresearch/nous-capybara-34b': { name: 'Nous: Capybara 34B', cw: 32000, cp: 0.0007, cc: 0.0028, unfilt: true }, 'jondurbin/airoboros-l2-70b': { name: 'Airoboros 70B', cw: 4096, cp: 0.0007, cc: 0.00095, unfilt: true }, 'migtissera/synthia-70b': { name: 'Synthia 70B', cw: 8192, cp: 0.00375, cc: 0.00375, unfilt: true }, - 'open-orca/mistral-7b-openorca': { name: 'Mistral OpenOrca 7B', cw: 8192, cp: 0.0002, cc: 0.0002, unfilt: true }, + 'open-orca/mistral-7b-openorca': { name: 'Mistral OpenOrca 7B', cw: 8192, cp: 0.0001425006, cc: 0.0001425006, unfilt: true }, 'teknium/openhermes-2-mistral-7b': { name: 'OpenHermes 2 Mistral 7B', cw: 4096, cp: 0.0002, cc: 0.0002, unfilt: true }, 'teknium/openhermes-2.5-mistral-7b': { name: 'OpenHermes 2.5 Mistral 7B', cw: 4096, cp: 0.0002, cc: 0.0002, unfilt: true }, 'pygmalionai/mythalion-13b': { name: 'Pygmalion: Mythalion 13B', cw: 8192, cp: 0.001125, cc: 0.001125, unfilt: true }, @@ -361,9 +363,9 @@ const orModelMap: { [id: string]: { name: string; cw: number; cp?: number; cc?: '01-ai/yi-34b-chat': { name: 'Yi 34B Chat', cw: 4096, cp: 0.0008, cc: 0.0008, unfilt: true }, '01-ai/yi-34b': { name: 'Yi 34B (base)', cw: 4096, cp: 0.0008, cc: 0.0008, unfilt: true }, '01-ai/yi-6b': { name: 'Yi 6B (base)', cw: 4096, cp: 0.00014, cc: 0.00014, unfilt: true }, - 'togethercomputer/stripedhyena-nous-7b': { name: 'StripedHyena Nous 7B', cw: 32000, cp: 0.0002, cc: 0.0002, unfilt: true }, - 'togethercomputer/stripedhyena-hessian-7b': { name: 'StripedHyena Hessian 7B (base)', cw: 32000, cp: 0.0002, cc: 0.0002, unfilt: true }, - 'mistralai/mixtral-8x7b': { name: 'Mistral: Mixtral 8x7B (base) (beta)', cw: 32000, cp: 0.0006, cc: 0.0006, unfilt: true }, + 'togethercomputer/stripedhyena-nous-7b': { name: 'StripedHyena Nous 7B', cw: 32768, cp: 0.0002, cc: 0.0002, unfilt: true }, + 'togethercomputer/stripedhyena-hessian-7b': { name: 'StripedHyena Hessian 7B (base)', cw: 32768, cp: 0.0002, cc: 0.0002, unfilt: true }, + 'mistralai/mixtral-8x7b': { name: 'Mistral: Mixtral 8x7B (base) (beta)', cw: 32768, cp: 0.0006, cc: 0.0006, unfilt: true }, 'anthropic/claude-2': { name: 'Anthropic: Claude v2.1', cw: 200000, cp: 0.008, cc: 0.024, unfilt: false }, 'anthropic/claude-2.0': { name: 'Anthropic: Claude v2.0', cw: 100000, cp: 0.008, cc: 0.024, unfilt: false }, 'anthropic/claude-instant-v1': { name: 'Anthropic: Claude Instant v1', cw: 100000, cp: 0.00163, cc: 0.00551, unfilt: false }, @@ -382,10 +384,10 @@ const orModelMap: { [id: string]: { name: string; cw: number; cp?: number; cc?: }; const orModelFamilyOrder = [ - // great models - 'mistralai/mixtral-8x7b-instruct', 'mistralai/mistral-7b-instruct', 'nousresearch/nous-capybara-7b', + // great models (pickes by hand, they're free) + 'mistralai/mistral-7b-instruct', 'nousresearch/nous-capybara-7b', // great orgs - 'huggingfaceh4/', 'openchat/', 'anthropic/', 'google/', 'openai/', 'meta-llama/', 'phind/', + 'huggingfaceh4/', 'openchat/', 'anthropic/', 'google/', 'mistralai/', 'openai/', 'meta-llama/', 'phind/', ]; export function openRouterModelFamilySortFn(a: { id: string }, b: { id: string }): number { diff --git a/src/modules/llms/vendors/ollama/OllamaAdministration.tsx b/src/modules/llms/vendors/ollama/OllamaAdministration.tsx index 2c0aa4b946..26378201e4 100644 --- a/src/modules/llms/vendors/ollama/OllamaAdministration.tsx +++ b/src/modules/llms/vendors/ollama/OllamaAdministration.tsx @@ -68,7 +68,7 @@ export function OllamaAdministration(props: { access: OllamaAccessSchema, onClos > {pullable.map(p => , )} @@ -118,7 +118,7 @@ export function OllamaAdministration(props: { access: OllamaAccessSchema, onClos {pullModelDescription} - +