Skip to content

Commit

Permalink
Merge pull request #260 from stanford-crfm/25-index-updates
Browse files Browse the repository at this point in the history
add nationality
  • Loading branch information
jxue16 authored Jan 24, 2025
2 parents fd820a8 + 492787b commit dbb41b2
Show file tree
Hide file tree
Showing 175 changed files with 16,106 additions and 13,925 deletions.
79 changes: 40 additions & 39 deletions assets/01ai.yaml
Original file line number Diff line number Diff line change
@@ -1,56 +1,57 @@
---
- type: model
name: Yi
organization: 01 AI
description: The Yi series models are large language models trained from scratch
by developers at 01 AI.
created_date: 2023-11-02
url: https://github.com/01-ai/Yi
model_card: https://huggingface.co/01-ai/Yi-34B
modality: text; text
- access: open
analysis: Evaluated on standard language benchmarks, common sense reasoning, and
reading comprehension in comparison to SoTA LLMs.
size: 34B parameters (dense)
created_date: 2023-11-02
dependencies: []
training_emissions: unknown
training_time: unknown
training_hardware: unknown
quality_control: Model underwent supervised fine-tuning, leading to a greater
diversity of responses.
access: open
description: The Yi series models are large language models trained from scratch
by developers at 01 AI.
feedback: https://huggingface.co/01-ai/Yi-34B/discussions
intended_uses: ''
license:
explanation: Model license can be found at https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE.
Code license is under Apache 2.0
value: custom
intended_uses: ''
prohibited_uses: none
modality: text; text
model_card: https://huggingface.co/01-ai/Yi-34B
monitoring: unknown
feedback: https://huggingface.co/01-ai/Yi-34B/discussions
- type: model
name: Yi-VL
name: Yi
nationality: France
organization: 01 AI
description: The Yi Vision Language (Yi-VL) model is the open-source, multimodal
version of the Yi Large Language Model (LLM) series, enabling content comprehension,
recognition, and multi-round conversations about images.
created_date: 2024-01-23
prohibited_uses: none
quality_control: Model underwent supervised fine-tuning, leading to a greater diversity
of responses.
size: 34B parameters (dense)
training_emissions: unknown
training_hardware: unknown
training_time: unknown
type: model
url: https://github.com/01-ai/Yi
model_card: https://huggingface.co/01-ai/Yi-VL-34B
modality: text; text
analysis: Yi-VL outperforms all existing open-source models in MMMU and CMMMU,
two advanced benchmarks that include massive multi-discipline multimodal questions
- access: open
analysis: Yi-VL outperforms all existing open-source models in MMMU and CMMMU, two
advanced benchmarks that include massive multi-discipline multimodal questions
(based on data available up to January 2024).
size: 34B parameters (dense)
created_date: 2024-01-23
dependencies: []
training_emissions: unknown
training_time: 10 days
training_hardware: 128 NVIDIA A800 (80G) GPUs
quality_control: unknown
access: open
description: The Yi Vision Language (Yi-VL) model is the open-source, multimodal
version of the Yi Large Language Model (LLM) series, enabling content comprehension,
recognition, and multi-round conversations about images.
feedback: https://huggingface.co/01-ai/Yi-VL-34B/discussions
intended_uses: ''
license:
explanation: Model license can be found at https://huggingface.co/01-ai/Yi-VL-34B/blob/main/LICENSE.
Code license is under Apache 2.0
value: custom
intended_uses: ''
prohibited_uses: ''
modality: text; text
model_card: https://huggingface.co/01-ai/Yi-VL-34B
monitoring: unknown
feedback: https://huggingface.co/01-ai/Yi-VL-34B/discussions
name: Yi-VL
nationality: France
organization: 01 AI
prohibited_uses: ''
quality_control: unknown
size: 34B parameters (dense)
training_emissions: unknown
training_hardware: 128 NVIDIA A800 (80G) GPUs
training_time: 10 days
type: model
url: https://github.com/01-ai/Yi
37 changes: 18 additions & 19 deletions assets/360.yaml
Original file line number Diff line number Diff line change
@@ -1,24 +1,23 @@
---
- type: model
name: 360 Zhinao
organization: 360 Security
description: 360 Zhinao is a multilingual LLM in Chinese and English with chat
capabilities.
created_date: 2024-05-23
url: https://arxiv.org/pdf/2405.13386
model_card: none
modality: text; text
- access: open
analysis: Achieved competitive performance on relevant benchmarks against other
7B models in Chinese, English, and coding tasks.
size: 7B parameters
created_date: 2024-05-23
dependencies: []
training_emissions: unknown
training_time: unknown
training_hardware: unknwon
quality_control: ''
access: open
license: unknown
description: 360 Zhinao is a multilingual LLM in Chinese and English with chat capabilities.
feedback: none
intended_uses: ''
prohibited_uses: ''
license: unknown
modality: text; text
model_card: none
monitoring: ''
feedback: none
name: 360 Zhinao
nationality: China
organization: 360 Security
prohibited_uses: ''
quality_control: ''
size: 7B parameters
training_emissions: unknown
training_hardware: unknwon
training_time: unknown
type: model
url: https://arxiv.org/pdf/2405.13386
145 changes: 74 additions & 71 deletions assets/adept.yaml
Original file line number Diff line number Diff line change
@@ -1,100 +1,103 @@
---
- type: model
name: ACT-1
organization: Adept
description: ACT-1 (ACtion Transformer) is a large-scale transformer model designed
and trained specifically for taking actions on computers (use software tools
APIs and websites) in response to the user's natural language commands.
- access: closed
analysis: ''
created_date:
explanation: The date the model was announced in the [[Adept blog post]](https://www.adept.ai/blog/act-1).
value: 2022-09-14
url: https://www.adept.ai/blog/act-1
model_card: none
dependencies: []
description: ACT-1 (ACtion Transformer) is a large-scale transformer model designed
and trained specifically for taking actions on computers (use software tools APIs
and websites) in response to the user's natural language commands.
feedback: ''
intended_uses: ''
license: unknown
modality: text; text
analysis: ''
model_card: none
monitoring: ''
name: ACT-1
nationality: USA
organization: Adept
prohibited_uses: ''
quality_control: ''
size: ''
dependencies: []
training_emissions: unknown
training_time: unknown
training_hardware: unknown
quality_control: ''
access: closed
license: unknown
training_time: unknown
type: model
url: https://www.adept.ai/blog/act-1
- access: open
analysis: Evaluated in comparison to LLaMA 2 and MPT Instruct, and outperforms both
on standard benchmarks.
created_date: 2023-09-07
dependencies: []
description: Persimmon is the most capable open-source, fully permissive model with
fewer than 10 billion parameters, as of its release date.
feedback: ''
intended_uses: ''
prohibited_uses: ''
license: Apache 2.0
modality: text; text
model_card: ''
monitoring: ''
feedback: ''
- type: model
name: Persimmon
nationality: USA
organization: Adept
description: Persimmon is the most capable open-source, fully permissive model
with fewer than 10 billion parameters, as of its release date.
created_date: 2023-09-07
url: https://www.adept.ai/blog/persimmon-8b
model_card: ''
modality: text; text
analysis: Evaluated in comparison to LLaMA 2 and MPT Instruct, and outperforms
both on standard benchmarks.
prohibited_uses: ''
quality_control: ''
size: 8B parameters (dense)
dependencies: []
training_emissions: ''
training_time: ''
training_hardware: ''
quality_control: ''
access: open
license: Apache 2.0
intended_uses: ''
prohibited_uses: ''
monitoring: ''
feedback: ''
- type: model
name: Fuyu
organization: Adept
training_time: ''
type: model
url: https://www.adept.ai/blog/persimmon-8b
- access: open
analysis: Evaluated on standard image understanding benchmarks.
created_date: 2023-10-17
dependencies: []
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
feedback: https://huggingface.co/adept/fuyu-8b/discussions
intended_uses: The model is intended for research purposes only.
license: CC-BY-NC-4.0
modality: image, text; text
analysis: Evaluated on standard image understanding benchmarks.
model_card: https://huggingface.co/adept/fuyu-8b
monitoring: ''
name: Fuyu
nationality: USA
organization: Adept
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.
quality_control: none
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
- type: model
name: Fuyu Heavy
organization: Adept
training_time: unknown
type: model
url: https://www.adept.ai/blog/fuyu-8b
- access: closed
analysis: Evaluated on the MMLU, GSM8K, MATH, and HumanEval benchmarks. According
to these benchmarks, Fuyu-Heavy is, as of release, the strongest multimodal model
trained outside of Google or OpenAI.
created_date: 2024-01-24
dependencies: []
description: Fuyu Heavy is a new multimodal model designed specifically for digital
agents.
created_date: 2024-01-24
url: https://www.adept.ai/blog/adept-fuyu-heavy
model_card: none
feedback: none
intended_uses: unknown
license: unknown
modality: image, text; text
analysis: Evaluated on the MMLU, GSM8K, MATH, and HumanEval benchmarks. According
to these benchmarks, Fuyu-Heavy is, as of release, the strongest multimodal
model trained outside of Google or OpenAI.
model_card: none
monitoring: ''
name: Fuyu Heavy
nationality: USA
organization: Adept
prohibited_uses: none
quality_control: none
size:
explanation: The size of the model is 10-20 times smaller than GPT-4V and Gemini
Ultra, as per announcement.
value: unknown
dependencies: []
training_emissions: unknown
training_time: unknown
training_hardware: unknown
quality_control: none
access: closed
license: unknown
intended_uses: unknown
prohibited_uses: none
monitoring: ''
feedback: none
training_time: unknown
type: model
url: https://www.adept.ai/blog/adept-fuyu-heavy
Loading

0 comments on commit dbb41b2

Please sign in to comment.