Merge branch 'main' into jonathan/1110-weekly-assets

assets/01ai.yaml

@@ -0,0 +1,22 @@
+---
+- type: model
+  name: Yi
+  organization: 01.AI
+  description: Yi is a LLM that can accept input/outputs in both English and Chinese.
+  created_date: 2023-11-02
+  url: https://github.com/01-ai/Yi
+  model_card: https://huggingface.co/01-ai/Yi-34B
+  modality: text; text
+  analysis: Evaluated on common sense reasoning and reading comprehension, analogous to LLaMA 2's analysis. 
+  size: 34B parameters (dense)
+  dependencies: []
+  training_emissions: unknown
+  training_time: unknown
+  training_hardware: unknown
+  quality_control: ''
+  access: open
+  license: Apache 2.0
+  intended_uses: Academic research and free commercial usage
+  prohibited_uses: ''
+  monitoring: none
+  feedback: https://huggingface.co/01-ai/Yi-34B/discussions

assets/adept.yaml

@@ -47,3 +47,24 @@
   prohibited_uses: ''
   monitoring: ''
   feedback: ''
+- type: model
+  name: Fuyu
+  organization: Adept
+  description: Fuyu is a small version of the multimodal model that powers Adept's core product.
+  created_date: 2023-10-17
+  url: https://www.adept.ai/blog/fuyu-8b
+  model_card: https://huggingface.co/adept/fuyu-8b
+  modality: image, text; text
+  analysis: Evaluated on standard image understanding benchmarks.
+  size: 8B parameters (dense)
+  dependencies: []
+  training_emissions: unknown
+  training_time: unknown
+  training_hardware: unknown
+  quality_control: none
+  access: open
+  license: CC BY NC 4.0
+  intended_uses: The model is intended for research purposes only.
+  prohibited_uses: The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.
+  monitoring: ''
+  feedback: https://huggingface.co/adept/fuyu-8b/discussions

assets/adobe.yaml

@@ -0,0 +1,88 @@
+---
+- type: model
+  name: Firefly Image 2
+  organization: Adobe
+  description: Firefly Image 2 is the next generation of generative AI for imaging, bringing significant advancements to creative control and quality, including new Text to Image capabilities now available in the popular Firefly web app where 90% of users are new to Adobe products.
+  created_date: 2023-10-10
+  url: https://firefly.adobe.com/
+  model_card: none
+  modality: text; image
+  analysis: ''
+  size: unknown
+  dependencies: []
+  training_emissions: unknown
+  training_time: unknown
+  training_hardware: unknown
+  quality_control: ''
+  access: closed
+  license: unknown
+  intended_uses: creative generation of digital art and images
+  prohibited_uses: AI/ML training, attempting to create abusive, illegal, or confidential content.
+  monitoring: ''
+  feedback: ''
+
+- type: model
+  name: Firefly Vector
+  organization: Adobe
+  description: Firefly Vector is the world’s first generative AI focused on producing vector graphics, bringing Adobe's vector graphic and generative AI expertise directly into Adobe Illustrator workflows with Text to Vector Graphic.
+  created_date: 2023-10-10
+  url: https://firefly.adobe.com/
+  model_card: none
+  modality: text; vector graphic
+  analysis: ''
+  size: unknown
+  dependencies: []
+  training_emissions: unknown
+  training_time: unknown
+  training_hardware: unknown
+  quality_control: ''
+  access: closed
+  license: unknown
+  intended_uses: creative generation of digital art and images
+  prohibited_uses: AI/ML training, attempting to create abusive, illegal, or confidential content.
+  monitoring: ''
+  feedback: ''
+
+- type: model
+  name: Firefly Design
+  organization: Adobe
+  description: Firefly Design powers instant generation of amazing quality template designs in Adobe Express with the new Text to Template capability.
+  created_date: 2023-10-10
+  url: https://firefly.adobe.com/
+  model_card: none
+  modality: text; template design
+  analysis: ''
+  size: unknown
+  dependencies: []
+  training_emissions: unknown
+  training_time: unknown
+  training_hardware: unknown
+  quality_control: ''
+  access: closed
+  license: unknown
+  intended_uses: creative generation of digital art and images
+  prohibited_uses: AI/ML training, attempting to create abusive, illegal, or confidential content.
+  monitoring: ''
+  feedback: ''
+
+- type: application
+  name: Firefly
+  organization: Adobe
+  description: Adobe Firefly is a standalone web application. It offers new ways to ideate, create, and communicate while significantly improving creative workflows using generative AI.
+  created_date: 2023-03-21
+  url: https://firefly.adobe.com/
+  dependencies: [Firefly Image 2, Firefly Vector, Firefly Design]
+  adaptation: ''
+  output_space: AI-generated creations
+  quality_control: ''
+  access: limited
+  license: unknown
+  terms_of_service: https://www.adobe.com/legal/licenses-terms/adobe-gen-ai-user-guidelines.html
+  intended_uses: creative generation of digital art and images
+  prohibited_uses: AI/ML training, attempting to create abusive, illegal, or confidential content.
+  monitoring: ''
+  feedback: ''
+  monthly_active_users: unknown
+  user_distribution: unknown
+  failures: unknown
+

assets/amazon.yaml

@@ -29,3 +29,24 @@
   monthly_active_users: ''
   user_distribution: ''
   failures: ''
+- type: model
+  name: FalconLite2
+  organization: Amazon
+  description: FalconLite2 is a fine-tuned and quantized Falcon language model, capable of processing long (up to 24K tokens) input sequences.
+  created_date: 2023-08-08
+  url: https://huggingface.co/amazon/FalconLite2
+  model_card: https://huggingface.co/amazon/FalconLite2
+  modality: text; text
+  analysis: Evaluated against benchmarks that are specifically designed to assess the capabilities of LLMs in handling longer contexts.
+  size: 40B parameters (dense)
+  dependencies: [Falcon]
+  training_emissions: unknown
+  training_time: unknown
+  training_hardware: unknown
+  quality_control: ''
+  access: open
+  license: Apache 2.0
+  intended_uses: ''
+  prohibited_uses: ''
+  monitoring: ''
+  feedback: https://huggingface.co/amazon/FalconLite2/discussions

assets/anthropic.yaml

@@ -512,7 +512,7 @@
   training_time: ''
   training_hardware: unknown
   quality_control: ''
-  access: open
+  access: limited
   license: ''
   intended_uses: Claude 2 tends to perform well at general, open-ended conversation;
     search, writing, editing, outlining, and summarizing text; coding; and providing
@@ -524,3 +524,24 @@
     where an incorrect answer would cause harm.
   monitoring: ''
   feedback: ''
+- type: model
+  name: Claude 2.1
+  organization: Anthropic
+  description: Claude 2.1 is an updated version of Claude 2, with an increased context window, less hallucination and tool use.
+  created_date: 2023-11-21
+  url: https://www.anthropic.com/index/claude-2-1
+  model_card: none
+  modality: text; text
+  analysis: Evaluated on open-ended conversation accuracy and long context question answering. In evaluations, Claude 2.1 demonstrated a 30% reduction in incorrect answers and a 3-4x lower rate of mistakenly concluding a document supports a particular claim.
+  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

assets/baai.yaml

@@ -45,3 +45,45 @@
   prohibited_uses: ''
   monitoring: ''
   feedback: ''
+- type: model
+  name: JudgeLM
+  organization: Beijing Academy of Artificial Intelligence
+  description: JudgeLM is a fine-tuned to be a scalable judge to evaluate LLMs efficiently and effectively in open-ended benchmarks.
+  created_date: 2023-10-26
+  url: https://arxiv.org/pdf/2310.17631.pdf
+  model_card: https://huggingface.co/BAAI/JudgeLM-13B-v1.0
+  modality: text; text
+  analysis: Evaluated on objective and reliability metrics.
+  size: 13B parameters (dense)
+  dependencies: [Vicuna, JudgeLM Dataset]
+  training_emissions: unknown
+  training_time: unknown
+  training_hardware: 8 A100 40GB NVIDIA GPUs
+  quality_control: ''
+  access: open
+  license: custom non-commercial license
+  intended_uses: Research on evaluating the performance of large language models and chatbots.
+  prohibited_uses: none
+  monitoring: none
+  feedback: https://huggingface.co/BAAI/JudgeLM-13B-v1.0/discussions
+- type: dataset
+  name: JudgeLM Dataset
+  organization: Beijing Academy of Artificial Intelligence
+  description: JudgeLM Dataset is a novel dataset replete with a rich variety of seed tasks, comprehensive answers from modern LLMs, answers’ grades from the teacher judge, and detailed reasons for judgments.
+  created_date: 2023-10-26
+  url: https://huggingface.co/datasets/BAAI/JudgeLM-100K
+  datasheet: ''
+  modality: text, text
+  size: 105k judge samples
+  sample: []
+  analysis: none
+  dependencies: [Alpaca, GPT-4, Dolly, ShareGPT, LLaMA, Vicuna]
+  included: ''
+  excluded: ''
+  quality_control: ''
+  access: open
+  license: CC BY NC 4.0
+  intended_uses: To be used to conduct instruction-tuning for language models and make the language model able to judge open-ended answer pairs.
+  prohibited_uses: none
+  monitoring: none
+  feedback: https://huggingface.co/datasets/BAAI/JudgeLM-100K/discussions

assets/baichuan.yaml

@@ -0,0 +1,22 @@
+---
+- type: model
+  name: Baichuan 2
+  organization: Baichuan Inc.
+  description: Baichuan 2 is a series of large-scale multilingual language models containing 7 billion and 13 billion parameters, trained from scratch, on 2.6 trillion tokens.
+  created_date: 2023-09-20
+  url: https://arxiv.org/pdf/2309.10305.pdf
+  model_card: none
+  modality: text; text
+  analysis: Evaluated on public benchmarks like MMLU, CMMLU, GSM8K, and HumanEval.
+  size: 13B parameters (dense)
+  dependencies: []
+  training_emissions: unknown
+  training_time: unknown
+  training_hardware: 1024 NVIDIA A800 GPUs
+  quality_control: ''
+  access: open
+  license: unknown
+  intended_uses: ''
+  prohibited_uses: ''
+  monitoring: none
+  feedback: https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1/discussions

assets/baidu.yaml

@@ -80,3 +80,26 @@
   prohibited_uses: unknown
   monitoring: none
   feedback: none
+- type: model
+  name: ERNIE 4.0
+  organization: Baidu
+  description: ERNIE-4.0 is a multimodal generalist foundation model.
+  created_date: 2023-10-17
+  url: 
+    explanation: No official statement from Baidu, so news release is provided.
+    value: https://www.prnewswire.com/news-releases/baidu-launches-ernie-4-0-foundation-model-leading-a-new-wave-of-ai-native-applications-301958681.html
+  model_card: none
+  modality: text; image, text, video
+  analysis: ''
+  size: unknown
+  dependencies: []
+  training_emissions: unknown
+  training_time: unknown
+  training_hardware: unknown
+  quality_control: ''
+  access: limited
+  license: unknown
+  intended_uses: unknown
+  prohibited_uses: unknown
+  monitoring: none
+  feedback: none

assets/beitech.yaml

@@ -0,0 +1,22 @@
+---
+- type: dataset
+  name: EXMODD
+  organization: Beijing Institute of Technology
+  description: EXMODD (Explanatory Multimodal Open-Domain Dialogue dataset) is a dataset built off the proposed MDCF (Multimodal Data Construction Framework).
+  created_date: 2023-10-17
+  url: https://arxiv.org/pdf/2310.10967.pdf
+  datasheet: none
+  modality: image, text
+  size: unknown
+  sample: []
+  analysis: Models fine-tuned on EXMODD and earlier dataset Image-Chat and then evaluated on Image-Chat validation set.
+  dependencies: [YFCC100M, Image-Chat]
+  included: ''
+  excluded: ''
+  quality_control: ''
+  access: open
+  license: MIT
+  intended_uses: ''
+  prohibited_uses: ''
+  monitoring: none
+  feedback: Feedback can be sent to authors via [email protected]

assets/bytedance.yaml

@@ -0,0 +1,22 @@
+---
+- type: model
+  name: SALMONN
+  organization: ByteDance, Tsinghua University
+  description: SALMONN is a large language model (LLM) enabling speech, audio event, and music inputs.
+  created_date: 2023-10-20
+  url: https://github.com/bytedance/SALMONN
+  model_card: https://huggingface.co/MSIIP/SALMONN
+  modality: audio, text; text
+  analysis: Evaluated on benchmarks pertaining to speech, music, and other audio recognition.
+  size: unknown
+  dependencies: [Whisper, BEATs, Vicuna]
+  training_emissions: unknown
+  training_time: unknown
+  training_hardware: unknown
+  quality_control: ''
+  access: open
+  license: Apache 2.0
+  intended_uses: ''
+  prohibited_uses: ''
+  monitoring: none
+  feedback: https://huggingface.co/MSIIP/SALMONN/discussions

assets/character.yaml

@@ -0,0 +1 @@
+

assets/cohere.yaml

@@ -449,3 +449,27 @@
   monthly_active_users: unknown
   user_distribution: unknown
   failures: unknown
+- type: model
+  name: Cohere Embedv3 (English)
+  organization: Cohere
+  description: As of release, Cohere Embedv3 is Cohere's latest and most advanced embeddings model.
+  created_date: 2023-11-02
+  url: https://txt.cohere.com/introducing-embed-v3/
+  model_card: https://huggingface.co/Cohere/Cohere-embed-english-v3.0
+  modality: text; text
+  analysis: Achieves SOTA performances on trusted MTEB and BEIR benchmarks.
+  size: unknown
+  dependencies: []
+  training_emissions: unknown
+  training_time: unknown
+  training_hardware: unknown
+  quality_control: ''
+  access:
+    explanation: "The model is available to the public through the Cohere Platform\
+      \ [[Cohere Platform]](https://cohere.ai/).\n"
+    value: limited
+  license: unknown
+  intended_uses: ''
+  prohibited_uses: ''
+  monitoring: none
+  feedback: https://huggingface.co/Cohere/Cohere-embed-english-v3.0/discussions

assets/columbia.yaml

@@ -20,3 +20,24 @@
   prohibited_uses: ''
   monitoring: ''
   feedback: ''
+- type: model
+  name: Ferret
+  organization: Columbia
+  description: Ferret is a Multimodal Large Language Model (MLLM) capable of understanding spatial referring of any shape or granularity within an image and accurately grounding open-vocabulary descriptions.
+  created_date: 2023-10-11
+  url: https://arxiv.org/pdf/2310.07704.pdf
+  model_card: none
+  modality: image, text; image, text
+  analysis: Evaluated on the object hallucination benchmark and compared to GPT-4V.
+  size: 13B parameters
+  dependencies: [CLIP, Vicuna]
+  training_emissions: unknown
+  training_time: 2.5 to 5 days
+  training_hardware: 8 A100 GPUs
+  quality_control: ''
+  access: open
+  license: unknown
+  intended_uses: ''
+  prohibited_uses: ''
+  monitoring: none
+  feedback: none