From b4547c61ba0082e6d1128c871e542a88256eb8bf Mon Sep 17 00:00:00 2001 From: jxue16 <105090474+jxue16@users.noreply.github.com> Date: Tue, 19 Mar 2024 22:19:00 -0700 Subject: [PATCH 1/3] weekly update(manual) --- assets/anthropic.yaml | 22 ++++++++++++++++++++ assets/apple.yaml | 22 ++++++++++++++++++++ assets/bigcode.yaml | 21 +++++++++++++++++++ assets/cognition.yaml | 22 ++++++++++++++++++++ assets/cohere.yaml | 22 ++++++++++++++++++++ assets/dibt.yaml | 22 ++++++++++++++++++++ assets/ideogram.yaml | 23 +++++++++++++++++++++ assets/inflection.yaml | 26 +++++++++++++++++++++-- assets/kotoba.yaml | 22 ++++++++++++++++++++ assets/nvidia.yaml | 22 ++++++++++++++++++++ assets/samba.yaml | 47 ++++++++++++++++++++++++++++++++++++++++++ assets/twelvelabs.yaml | 21 +++++++++++++++++++ assets/xai.yaml | 9 +++----- js/main.js | 6 ++++++ 14 files changed, 299 insertions(+), 8 deletions(-) create mode 100644 assets/apple.yaml create mode 100644 assets/cognition.yaml create mode 100644 assets/dibt.yaml create mode 100644 assets/ideogram.yaml create mode 100644 assets/kotoba.yaml create mode 100644 assets/samba.yaml diff --git a/assets/anthropic.yaml b/assets/anthropic.yaml index 4d2dff3d..e7f26d83 100644 --- a/assets/anthropic.yaml +++ b/assets/anthropic.yaml @@ -570,3 +570,25 @@ monthly_active_users: unknown user_distribution: unknown failures: unknown +- type: model + name: Claude 3 + organization: Anthropic + description: The Claude 3 model family is a collection of models which sets new industry benchmarks across a wide range of cognitive tasks. + created_date: 2024-03-04 + url: https://www.anthropic.com/news/claude-3-family + model_card: https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf + modality: image, text; code, text + analysis: Evaluated on reasoning, math, coding, reading comprehension, and question answering, outperforming GPT-4 on standard benchmarks. + size: unknown + dependencies: [] + training_emissions: unknown + training_time: unknown + training_hardware: unknown + quality_control: Pre-trained on diverse dataset and aligned with Constitutional AI technique. + access: limited + license: unknown + intended_uses: Claude models excel at open-ended conversation and collaboration on ideas, and also perform exceptionally well in coding tasks and when working with text - whether searching, writing, editing, outlining, or summarizing. + prohibited_uses: Prohibited uses include, but are not limited to, political campaigning or lobbying, surveillance, social scoring, criminal justice decisions, law enforcement, and decisions related to financing, employment, and housing. + monitoring: '' + feedback: none + diff --git a/assets/apple.yaml b/assets/apple.yaml new file mode 100644 index 00000000..69fffcdb --- /dev/null +++ b/assets/apple.yaml @@ -0,0 +1,22 @@ +--- +- type: model + name: MM1 + organization: Apple + description: MM1 is a family of multimodal models, including both dense variants up to 30B and mixture-of-experts (MoE) variants up to 64B. + created_date: 2024-03-16 + url: https://arxiv.org/pdf/2403.09611.pdf + model_card: none + modality: image, text; text + analysis: Evaluated on image captioning and visual question answering across many benchmarks. + size: 30B parameters (dense) + dependencies: [] + training_emissions: unknown + training_time: unknown + training_hardware: unknown + quality_control: '' + access: closed + license: unknown + intended_uses: '' + prohibited_uses: '' + monitoring: '' + feedback: none diff --git a/assets/bigcode.yaml b/assets/bigcode.yaml index 15df7e93..b61bd412 100644 --- a/assets/bigcode.yaml +++ b/assets/bigcode.yaml @@ -71,3 +71,24 @@ prohibited_uses: '' monitoring: '' feedback: '' +- type: model + name: StarCoder2 + organization: BigCode + description: A 15 billion parameter language model trained on 600+ programming languages from The Stack v2. The training was carried out using the Fill-in-the-Middle objective on 4+ trillion tokens. + created_date: 2024-02-28 + url: https://www.servicenow.com/company/media/press-room/huggingface-nvidia-launch-starcoder2.html + model_card: https://huggingface.co/bigcode/starcoder2-15b + modality: text; text + analysis: unknown + size: 15B parameters (dense) + dependencies: [The Stack v2] + training_emissions: unknown + training_time: unknown + training_hardware: 1024 x H100 GPUs + quality_control: The model was filtered for permissive licenses and code with no license only. A search index is provided to identify where generated code came from to apply the proper attribution. + access: open + license: BigCode OpenRail-M + intended_uses: Intended to generate code snippets from given context, but not for writing actual functional code directly. + prohibited_uses: Should not be used as a way to write fully functioning code without modification or verification. + monitoring: unknown + feedback: https://huggingface.co/bigcode/starcoder2-15b/discussions diff --git a/assets/cognition.yaml b/assets/cognition.yaml new file mode 100644 index 00000000..284ba199 --- /dev/null +++ b/assets/cognition.yaml @@ -0,0 +1,22 @@ +--- +- type: model + name: Devin + organization: Cognition Labs + description: Devin is the world’s first fully autonomous AI software engineer. + created_date: 2024-03-12 + url: https://www.cognition-labs.com/introducing-devin + model_card: none + modality: text; code + analysis: Evaluated on SWE-Bench, a challenging software engineering benchmark, where Devin outperforms major state of the art models unassisted. + size: unknown + dependencies: [] + training_emissions: unknown + training_time: unknown + training_hardware: unknown + quality_control: '' + access: limited + license: unknown + intended_uses: '' + prohibited_uses: '' + monitoring: '' + feedback: none diff --git a/assets/cohere.yaml b/assets/cohere.yaml index 43d175a9..6af4f1ee 100644 --- a/assets/cohere.yaml +++ b/assets/cohere.yaml @@ -474,3 +474,25 @@ prohibited_uses: '' monitoring: none feedback: https://huggingface.co/Cohere/Cohere-embed-english-v3.0/discussions +- type: model + name: Command-R + organization: Cohere + description: Command-R is a scalable generative model targeting RAG and Tool Use to enable production-scale AI for enterprise. + created_date: 2024-03-11 + url: https://txt.cohere.com/command-r/ + model_card: https://huggingface.co/CohereForAI/c4ai-command-r-v01 + modality: text; text + analysis: none + size: 35B parameters (dense) + dependencies: [] + training_emissions: unknown + training_time: unknown + training_hardware: unknown + quality_control: '' + access: open + license: CC BY NC 4.0 + intended_uses: '' + prohibited_uses: '' + monitoring: '' + feedback: https://huggingface.co/CohereForAI/c4ai-command-r-v01/discussions + diff --git a/assets/dibt.yaml b/assets/dibt.yaml new file mode 100644 index 00000000..1ae8dff3 --- /dev/null +++ b/assets/dibt.yaml @@ -0,0 +1,22 @@ +--- +- type: dataset + name: 10k_prompts_ranked + organization: Data is Better Together + description: 10k_prompts_ranked is a dataset of prompts with quality rankings created by 314 members of the open-source ML community using Argilla, an open-source tool to label data. + created_date: 2024-02-27 + url: https://huggingface.co/blog/community-datasets + datasheet: https://huggingface.co/datasets/DIBT/10k_prompts_ranked + modality: text + size: 10k examples + sample: [] + analysis: none + dependencies: [] + included: '' + excluded: '' + quality_control: '' + access: open + license: unknown + intended_uses: Training and evaluating language models on prompt ranking tasks and as a dataset that can be filtered only to include high-quality prompts. These can serve as seed data for generating synthetic prompts and generations. + prohibited_uses: This dataset only contains rankings for prompts, not prompt/response pairs so it is not suitable for direct use for supervised fine-tuning of language models. + monitoring: '' + feedback: https://huggingface.co/datasets/DIBT/10k_prompts_ranked/discussions diff --git a/assets/ideogram.yaml b/assets/ideogram.yaml new file mode 100644 index 00000000..e109f7a7 --- /dev/null +++ b/assets/ideogram.yaml @@ -0,0 +1,23 @@ +--- +- type: model + name: Ideogram 1.0 + organization: Ideogram AI + description: Ideogram 1.0 is Ideogram’s most advanced text-to-image model, as of release. + created_date: 2024-02-28 + url: https://about.ideogram.ai/1.0 + model_card: none + modality: text; image + analysis: Compared to DALL·E 3 based on a qualitative user comparison. + size: unknown + dependencies: [] + training_emissions: unknown + training_time: unknown + training_hardware: unknown + quality_control: '' + access: limited + license: unknown + intended_uses: '' + prohibited_uses: '' + monitoring: '' + feedback: none + diff --git a/assets/inflection.yaml b/assets/inflection.yaml index 84f958a7..22ca6d6c 100644 --- a/assets/inflection.yaml +++ b/assets/inflection.yaml @@ -2,7 +2,7 @@ - type: model name: Inflection-1 organization: Inflection AI - description: Inflection AI's in-house LLM, which powers Pi and will soon be available + description: Inflection AI's first version of its in-house LLM. via Inflection AI's conversational API. created_date: 2023-06-22 url: https://inflection.ai/inflection-1 @@ -31,7 +31,7 @@ in emotional intelligence. created_date: 2023-05-02 url: https://inflection.ai/press - dependencies: [Inflection-1] + dependencies: [Inflection-2.5] adaptation: '' output_space: natural language text responses quality_control: '' @@ -70,3 +70,25 @@ prohibited_uses: '' monitoring: '' feedback: none +- type: model + name: Inflection-2.5 + organization: Inflection AI + description: Inflection-2.5 is an upgraded in-house model that is competitive with all the world's leading LLMs, as of release, like GPT-4 and Gemini. + created_date: 2024-03-07 + url: https://inflection.ai/inflection-2-5 + model_card: none + modality: text; text + analysis: Evaluated on standard LLM and technical benchmarks in comparison to Inflection-1 and GPT-4, along with advanced STEM examinations. + size: unknown + dependencies: [] + training_emissions: unknown + training_time: unknown + training_hardware: unknown + quality_control: '' + access: limited + license: unknown + intended_uses: '' + prohibited_uses: '' + monitoring: '' + feedback: none + diff --git a/assets/kotoba.yaml b/assets/kotoba.yaml new file mode 100644 index 00000000..2b06dcd7 --- /dev/null +++ b/assets/kotoba.yaml @@ -0,0 +1,22 @@ +--- +- type: model + name: Kotoba Speech + organization: Kotoba Tech + description: Kotoba-Speech is a Transformer-based speech generative model that supports fluent text-to-speech generation in Japanese and one-shot voice cloning through speech prompt. + created_date: 2024-03-13 + url: https://huggingface.co/kotoba-tech/kotoba-speech-v0.1 + model_card: https://huggingface.co/kotoba-tech/kotoba-speech-v0.1 + modality: text; audio + analysis: unknown + size: 1.2B parameters (dense) + dependencies: [] + training_emissions: unknown + training_time: unknown + training_hardware: unknown + quality_control: '' + access: open + license: Apache 2.0 + intended_uses: '' + prohibited_uses: '' + monitoring: unknown + feedback: https://huggingface.co/kotoba-tech/kotoba-speech-v0.1/discussions \ No newline at end of file diff --git a/assets/nvidia.yaml b/assets/nvidia.yaml index ead8e92e..83abb2ca 100644 --- a/assets/nvidia.yaml +++ b/assets/nvidia.yaml @@ -88,3 +88,25 @@ prohibited_uses: '' monitoring: '' feedback: '' +- type: model + name: Nemotron 4 + organization: Nvidia + description: Nemotron 4 is a 15-billion-parameter large multilingual language model trained on 8 trillion text tokens. + created_date: 2024-02-27 + url: https://arxiv.org/pdf/2402.16819.pdf + model_card: none + modality: text; code, text + analysis: Evaluated on standard LLM benchmarks across a range of fields like reasoning, code generation, and mathematical skills. + size: 15B parameters (dense) + dependencies: [] + training_emissions: unknown + training_time: 13 days + training_hardware: 384 DGX H100 nodes, each with 8 H100 80GB SXM5 GPUs + quality_control: Deduplication and quality filtering techniques are applied to the training dataset. + access: open + license: unknown + intended_uses: '' + prohibited_uses: '' + monitoring: unknown + feedback: none + diff --git a/assets/samba.yaml b/assets/samba.yaml new file mode 100644 index 00000000..6fd69ddf --- /dev/null +++ b/assets/samba.yaml @@ -0,0 +1,47 @@ +--- +- type: model + name: SambaLingo + organization: Samba Nova Systems + description: SambaLingo is a suite of models that adapt Llama 2 to a diverse set of 9 languages. + created_date: 2024-02-26 + url: https://sambanova.ai/blog/sambalingo-open-source-language-experts + model_card: + explanation: The Arabic language model card is given, but there exist one for each of the other 8 languages in the collection. + value: https://huggingface.co/sambanovasystems/SambaLingo-Arabic-Base + modality: text; text + analysis: Evaluated on open source multilingual model benchmarks. + size: unknown + dependencies: [LLaMA 2] + training_emissions: unknown + training_time: unknown + training_hardware: unknown + quality_control: '' + access: open + license: LLaMA 2 + intended_uses: '' + prohibited_uses: SambaLingo should not be used for mission-critical applications, applications involving the safety of others, and highly critical decisions. + monitoring: '' + feedback: + explanation: The Arabic language model feedback is given, but there exists one for each of the other 8 languages in the collection. + value: https://huggingface.co/sambanovasystems/SambaLingo-Arabic-Base/discussions +- type: model + name: Samba 1 + organization: Samba Nova Systems + description: Samba 1 is a trillion parameter generative AI model using a Composition of Experts architecture. + created_date: 2024-02-28 + url: https://sambanova.ai/blog/samba-1-composition-of-experts-mode + model_card: none + modality: text; text + analysis: unknown + size: 1T parameters (dense) + dependencies: [LLaMA 2, Mistral, Falcon-180B, Deepseek, BLOOM, LLaVA, CLIP] + training_emissions: unknown + training_time: unknown + training_hardware: unknown + quality_control: '' + access: limited + license: unknown + intended_uses: '' + prohibited_uses: '' + monitoring: unknown + feedback: none diff --git a/assets/twelvelabs.yaml b/assets/twelvelabs.yaml index 0925ae0b..9a6e5f88 100644 --- a/assets/twelvelabs.yaml +++ b/assets/twelvelabs.yaml @@ -20,3 +20,24 @@ prohibited_uses: '' monitoring: none feedback: none +- type: model + name: Marengo 2.6 + organization: Twelve Labs + description: Marengo 2.6 is a new state-of-the-art (SOTA) multimodal foundation model capable of performing any-to-any search tasks, including Text-To-Video, Text-To-Image, Text-To-Audio, Audio-To-Video, Image-To-Video, and more.  + created_date: 2024-03-01 + url: https://www.twelvelabs.io/blog/introducing-marengo-2-6 + model_card: none + modality: audio, image, text; audio, image, video + analysis: Marengo-2.6 sets new benchmarks in zero-shot text-to-video, text-to-image, and text-to-audio retrieval tasks with a single embedding model. + size: unknown + dependencies: [] + training_emissions: unknown + training_time: unknown + training_hardware: unknown + quality_control: '' + access: open + license: unknown + intended_uses: '' + prohibited_uses: '' + monitoring: '' + feedback: none diff --git a/assets/xai.yaml b/assets/xai.yaml index f2a1bfea..8e0dc631 100644 --- a/assets/xai.yaml +++ b/assets/xai.yaml @@ -9,17 +9,14 @@ modality: text; text analysis: Grok-1 was evaluated on a range of reasoning benchmark tasks and on curated foreign mathematic examination questions. - size: - explanation: No model size specified, but Grok-1 is larger than predecessor - Grok-0 (33B parameters), as stated in the Grok announcement at https://x.ai/. - value: unknown + size: 314B parameters (dense) dependencies: [] training_emissions: unknown training_time: unknown training_hardware: unknown quality_control: none - access: limited - license: unknown + access: open + license: Apache 2.0 intended_uses: Grok-1 is intended to be used as the engine behind Grok for natural language processing tasks including question answering, information retrieval, creative writing and coding assistance. diff --git a/js/main.js b/js/main.js index 82ed2888..fb02302d 100644 --- a/js/main.js +++ b/js/main.js @@ -676,6 +676,7 @@ function loadAssetsAndRenderPageContent() { 'assets/aleph_alpha.yaml', 'assets/alibaba.yaml', 'assets/anthropic.yaml', + 'assets/apple.yaml', 'assets/argonne.yaml', 'assets/assembly.yaml', 'assets/baai.yaml', @@ -688,6 +689,7 @@ function loadAssetsAndRenderPageContent() { 'assets/cerebras.yaml', 'assets/character.yaml', 'assets/cmu.yaml', + 'assets/cognition.yaml', 'assets/cohere.yaml', 'assets/continue.yaml', 'assets/cresta.yaml', @@ -698,6 +700,7 @@ function loadAssetsAndRenderPageContent() { 'assets/epfl.yaml', 'assets/deepmind.yaml', 'assets/deepseek.yaml', + 'assets/dibt.yaml', 'assets/duckduckgo.yaml', 'assets/duolingo.yaml', 'assets/eleutherai.yaml', @@ -706,10 +709,12 @@ function loadAssetsAndRenderPageContent() { 'assets/hubspot.yaml', 'assets/huggingface.yaml', 'assets/idea.yaml', + 'assets/ideogram.yaml', 'assets/instacart.yaml', 'assets/juni.yaml', 'assets/kakaobrain.yaml', 'assets/khan.yaml', + 'assets/kotoba.yaml', 'assets/laion.yaml', 'assets/latitude.yaml', 'assets/linkedin.yaml', @@ -733,6 +738,7 @@ function loadAssetsAndRenderPageContent() { 'assets/quora.yaml', 'assets/robin.yaml', 'assets/salesforce.yaml', + 'assets/samba.yaml', 'assets/sana.yaml', 'assets/shanghai.yaml', 'assets/shop.yaml', From 26cf299a9e69b1ec84a43c5c83fdf402f48386fc Mon Sep 17 00:00:00 2001 From: jxue16 <105090474+jxue16@users.noreply.github.com> Date: Tue, 19 Mar 2024 22:51:44 -0700 Subject: [PATCH 2/3] GPT test assets --- assets/bytedance.yaml | 21 +++++++++++++++++++++ assets/cagliostro.yaml | 22 ++++++++++++++++++++++ assets/nous.yaml | 42 ++++++++++++++++++++++++++++++++++++++++++ assets/stability.yaml | 21 +++++++++++++++++++++ js/main.js | 1 + 5 files changed, 107 insertions(+) create mode 100644 assets/cagliostro.yaml diff --git a/assets/bytedance.yaml b/assets/bytedance.yaml index e99c236e..29973a3b 100644 --- a/assets/bytedance.yaml +++ b/assets/bytedance.yaml @@ -22,3 +22,24 @@ prohibited_uses: '' monitoring: none feedback: https://huggingface.co/MSIIP/SALMONN/discussions +- type: model + name: SDXL-Lightning + organization: ByteDance + description: SDXL-Lightning is a lightning-fast text-to-image generation model. It can generate high-quality 1024px images in a few steps. The models are distilled from stabilityai/stable-diffusion-xl-base-1.0. This repository contains checkpoints for 1-step, 2-step, 4-step, and 8-step distilled models. + created_date: 2024-02-21 + url: https://arxiv.org/pdf/2402.13929.pdf + model_card: https://huggingface.co/ByteDance/SDXL-Lightning + modality: text; image + analysis: Evaluated via qualitative comparison relative to other SoTA image generation models. + size: unknown + dependencies: [Stable Diffusion XL] + training_emissions: unknown + training_time: unknown + training_hardware: 64 A100 80G GPUs + quality_control: unknown + access: open + license: OpenRail++ + intended_uses: The model can be used for fast, high-quality text-to-image generation. It supports 1-step, 2-step, 4-step, and 8-step distilled models which provide varying generation quality. + prohibited_uses: unknown + monitoring: unknown + feedback: https://huggingface.co/ByteDance/SDXL-Lightning/discussions diff --git a/assets/cagliostro.yaml b/assets/cagliostro.yaml new file mode 100644 index 00000000..738dcaf5 --- /dev/null +++ b/assets/cagliostro.yaml @@ -0,0 +1,22 @@ +--- +- type: model + name: Animagine XL 3.1 + organization: Cagliostro Research Lab + description: An open-source, anime-themed text-to-image model enhanced to generate higher quality anime-style images with a broader range of characters from well-known anime series, an optimized dataset, and new aesthetic tags for better image creation. + created_date: 2024-03-18 + url: https://cagliostrolab.net/posts/animagine-xl-v31-release + model_card: https://huggingface.co/cagliostrolab/animagine-xl-3.1 + modality: text; image + analysis: unknown + size: unknown + dependencies: [Animagine XL 3.0] + training_emissions: unknown + training_time: Approximately 15 days, totaling over 350 GPU hours. + training_hardware: 2x A100 80GB GPUs + quality_control: The model undergoes pretraining, first stage finetuning, and second stage finetuning for refining and improving aspects such as hand and anatomy rendering. + access: open + license: Fair AI Public License 1.0-SD + intended_uses: Generating high-quality anime images from textual prompts. Useful for anime fans, artists, and content creators. + prohibited_uses: Not suitable for creating realistic photos or for users who expect high-quality results from short or simple prompts. + monitoring: unknown + feedback: https://huggingface.co/cagliostrolab/animagine-xl-3.1/discussions diff --git a/assets/nous.yaml b/assets/nous.yaml index 4c41172a..3c8ccc8e 100644 --- a/assets/nous.yaml +++ b/assets/nous.yaml @@ -22,3 +22,45 @@ prohibited_uses: '' monitoring: unknown feedback: https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO/discussions +- type: model + name: Hermes 2 Pro-Mistral + organization: Nous + description: Hermes 2 Pro on Mistral 7B is an upgraded, retrained version of Nous Hermes 2. This improved version excels at function calling, JSON Structured Outputs, and several other areas, scoring positively on various benchmarks. + created_date: 2024-03-10 + url: https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B + model_card: https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B + modality: text; text + analysis: The model was examined across a range of benchmarks including GPT4All, AGIEval, BigBench, TruthfulQA and in-house evaluations of function calling and JSON mode. + size: 7B parameters (dense) + dependencies: [Mistral, OpenHermes 2.5 Dataset, Nous Hermes 2] + training_emissions: unknown + training_time: unknown + training_hardware: unknown + quality_control: The model was evaluated across multiple tasks, displaying notable scores in GPT4All, AGIEval, BigBench, and TruthfulQA. It also has a high score on function calling and JSON mode, indicating the robustness of its capabilities. + access: open + license: Apache 2.0 + intended_uses: The model is intended for general task and conversation capabilities, function calling, and JSON structured outputs. + prohibited_uses: unknown + monitoring: unknown + feedback: https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B/discussions +- type: model + name: Genstruct + organization: Nous + description: Genstruct is an instruction-generation model, designed to create valid instructions given a raw text corpus. This enables the creation of new, partially synthetic instruction finetuning datasets from any raw-text corpus. This work was inspired by Ada-Instruct and the model is also trained to generate questions involving complex scenarios that require detailed reasoning. + created_date: 2024-03-07 + url: https://huggingface.co/NousResearch/Genstruct-7B + model_card: https://huggingface.co/NousResearch/Genstruct-7B + modality: text; text + analysis: unknown + size: 7B parameters (dense) + dependencies: [] + training_emissions: unknown + training_time: unknown + training_hardware: unknown + quality_control: unknown + access: open + license: Apache 2.0 + intended_uses: The model is intended for instruction-generation, creating questions involving complex scenarios and generating reasoning steps for those questions. + prohibited_uses: unknown + monitoring: unknown + feedback: https://huggingface.co/NousResearch/Genstruct-7B/discussions diff --git a/assets/stability.yaml b/assets/stability.yaml index 936175db..8af18dd3 100644 --- a/assets/stability.yaml +++ b/assets/stability.yaml @@ -171,3 +171,24 @@ monthly_active_users: '' user_distribution: '' failures: '' +- type: model + name: Stable Video 3D + organization: Stability AI + description: Stable Video 3D (SV3D) is a generative model based on Stable Video Diffusion that takes in a still image of an object as a conditioning frame, and generates an orbital video of that object. + created_date: 2024-03-18 + url: https://stability.ai/news/introducing-stable-video-3d + model_card: https://huggingface.co/stabilityai/sv3d + modality: image; video + analysis: unknown + size: unknown + dependencies: [Objaverse] + training_emissions: unknown + training_time: unknown + training_hardware: unknown + quality_control: unknown + access: open + license: StabilityAI Non-Commercial Research Community License + intended_uses: This model is intended to be used for generating orbital videos of objects from still images. + prohibited_uses: The model should not be used for generating factual or true representations of people or events, or in any way that violates Stability AIs Acceptable Use Policy. + monitoring: unknown + feedback: https://huggingface.co/stabilityai/sv3d/discussions diff --git a/js/main.js b/js/main.js index fb02302d..86ec39e4 100644 --- a/js/main.js +++ b/js/main.js @@ -686,6 +686,7 @@ function loadAssetsAndRenderPageContent() { 'assets/bigscience.yaml', 'assets/bloomberg.yaml', 'assets/brex.yaml', + 'assets/cagliostro.yaml', 'assets/cerebras.yaml', 'assets/character.yaml', 'assets/cmu.yaml', From 96feefbfbee9b759b1a74a95e686614dcd8620c7 Mon Sep 17 00:00:00 2001 From: jxue16 <105090474+jxue16@users.noreply.github.com> Date: Wed, 27 Mar 2024 14:37:52 -0700 Subject: [PATCH 3/3] resolve changes --- assets/anthropic.yaml | 2 +- assets/nvidia.yaml | 2 +- assets/samba.yaml | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/assets/anthropic.yaml b/assets/anthropic.yaml index e7f26d83..b6ce7316 100644 --- a/assets/anthropic.yaml +++ b/assets/anthropic.yaml @@ -577,7 +577,7 @@ created_date: 2024-03-04 url: https://www.anthropic.com/news/claude-3-family model_card: https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf - modality: image, text; code, text + modality: image, text; text analysis: Evaluated on reasoning, math, coding, reading comprehension, and question answering, outperforming GPT-4 on standard benchmarks. size: unknown dependencies: [] diff --git a/assets/nvidia.yaml b/assets/nvidia.yaml index 83abb2ca..b498cc4d 100644 --- a/assets/nvidia.yaml +++ b/assets/nvidia.yaml @@ -101,7 +101,7 @@ dependencies: [] training_emissions: unknown training_time: 13 days - training_hardware: 384 DGX H100 nodes, each with 8 H100 80GB SXM5 GPUs + training_hardware: 3072 H100 80GB SXM5 GPUs across 384 DGX H100 nodes quality_control: Deduplication and quality filtering techniques are applied to the training dataset. access: open license: unknown diff --git a/assets/samba.yaml b/assets/samba.yaml index 6fd69ddf..3a60daa7 100644 --- a/assets/samba.yaml +++ b/assets/samba.yaml @@ -11,7 +11,7 @@ modality: text; text analysis: Evaluated on open source multilingual model benchmarks. size: unknown - dependencies: [LLaMA 2] + dependencies: [Llama 2] training_emissions: unknown training_time: unknown training_hardware: unknown @@ -34,7 +34,7 @@ modality: text; text analysis: unknown size: 1T parameters (dense) - dependencies: [LLaMA 2, Mistral, Falcon-180B, Deepseek, BLOOM, LLaVA, CLIP] + dependencies: [Llama 2, Mistral, Falcon-180B, Deepseek, BLOOM, LLaVA, CLIP] training_emissions: unknown training_time: unknown training_hardware: unknown