Skip to content

Commit

Permalink
Merge pull request #106 from llm-jp/f/japanese-stable-vlm
Browse files Browse the repository at this point in the history 
F/japanese stable vlm
  • Loading branch information
@kaisugi
kaisugi authored Dec 3, 2023
2 parents 87a53af + 165e120 commit 8b3ae02
Show file tree
Hide file tree
Showing 3 changed files with 15 additions and 6 deletions.
7 changes: 5 additions & 2 deletions README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -209,8 +209,9 @@

| | モデル | 学習画像/テキスト | 開発元 | ライセンス | HuggingFace ですぐ使える？ |
|:---|:---:|:---:|:---:|:---:|:---:|
| [Heron](https://prtimes.jp/main/html/rd/p/000000034.000098132.html) | BLIP または GIT | LLaVA-Instruct-150K-JA, Japanese STAIR Captions, Japanese Visual Genome VQA dataset | Turing | CC BY-NC 4.0 | ◯ ([blip-ja-stablelm-base-7b-v0](https://huggingface.co/turing-motors/heron-chat-blip-ja-stablelm-base-7b-v0), [git-ja-stablelm-base-7b-v0](https://huggingface.co/turing-motors/heron-chat-git-ja-stablelm-base-7b-v0), [git-ELYZA-fast-7b-v0](https://huggingface.co/turing-motors/heron-chat-git-ELYZA-fast-7b-v0)) |
| [Japanese InstructBLIP Alpha](https://ja.stability.ai/blog/japanese-instructblip-alpha) | InstructBLIP | Japanese CC12M, STAIR Captions, Japanese Visual Genome VQA dataset | Stability AI | [独自のライセンス](https://huggingface.co/stabilityai/japanese-instructblip-alpha/blob/main/LICENSE) | [◯](https://huggingface.co/stabilityai/japanese-instructblip-alpha) |
| [Japanese Stable VLM](https://ja.stability.ai/blog/japanese-stable-vlm) | LLaVA-1.5 | Japanese CC12M, STAIR Captions, Japanese Visual Genome VQA dataset | Stability AI | STABILITY AI JAPANESE STABLE VLM COMMUNITY LICENSE | [◯](https://huggingface.co/stabilityai/japanese-stable-vlm) |
| [Heron](https://github.com/turingmotors/heron/blob/main/docs/README_JP.md) | BLIP または GIT | LLaVA-Instruct-150K-JA, Japanese STAIR Captions, Japanese Visual Genome VQA dataset | Turing | CC BY-NC 4.0 | ◯ ([blip-ja-stablelm-base-7b-v0](https://huggingface.co/turing-motors/heron-chat-blip-ja-stablelm-base-7b-v0), [git-ja-stablelm-base-7b-v0](https://huggingface.co/turing-motors/heron-chat-git-ja-stablelm-base-7b-v0), [git-ELYZA-fast-7b-v0](https://huggingface.co/turing-motors/heron-chat-git-ELYZA-fast-7b-v0)) |
| [Japanese InstructBLIP Alpha](https://ja.stability.ai/blog/japanese-instructblip-alpha) | InstructBLIP | Japanese CC12M, STAIR Captions, Japanese Visual Genome VQA dataset | Stability AI | JAPANESE STABLELM RESEARCH LICENSE | [◯](https://huggingface.co/stabilityai/japanese-instructblip-alpha) |
| [rinna MiniGPT-4](https://rinna.co.jp/news/2023/07/20230731.html) [^11] | MiniGPT-4 | CC12M, COCO 2014, Visual Genome, STAIR Captions, Japanese Visual Genome VQA dataset | rinna | MIT | [◯](https://huggingface.co/rinna/bilingual-gpt-neox-4b-minigpt4) |

<a id="multimodal-others"></a>
Expand Down Expand Up @@ -283,10 +284,12 @@
| BLIP-2 | 2023.01.30 | ICML 2023 | [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://arxiv.org/abs/2301.12597) |
| Llama | 2023.02.27 | - | [LLaMA: Open and Efficient Foundation Language Models](https://arxiv.org/abs/2302.13971) |
| GPT-4 | 2023.03.15 | - | [GPT-4 Technical Report](https://arxiv.org/abs/2303.08774) |
| LLaVA | 2023.04.17 | NeurIPS 2023 | [Visual Instruction Tuning](https://arxiv.org/abs/2304.08485) |
| MiniGPT-4 | 2023.04.20 | - | [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://arxiv.org/abs/2304.10592) |
| InstructBLIP | 2023.05.11 | - | [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://arxiv.org/abs/2305.06500) |
| RWKV | 2023.05.22 | - | [RWKV: Reinventing RNNs for the Transformer Era](https://arxiv.org/abs/2305.13048) |
| Llama 2 | 2023.07.18 | - | [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://arxiv.org/abs/2307.09288) |
| LLaVA-1.5 | 2023.10.05 | - | [Improved Baselines with Visual Instruction Tuning](https://arxiv.org/abs/2310.03744) |

<a id="contributors"></a>
## コントリビューター
Expand Down
7 changes: 5 additions & 2 deletions README_en.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -209,8 +209,9 @@ Please point out any errors on the [issues page](https://github.com/llm-jp/aweso

| | Architecture | Training Data | Developer | License | HuggingFace? |
|:---|:---:|:---:|:---:|:---:|:---:|
| [Heron](https://prtimes.jp/main/html/rd/p/000000034.000098132.html) | BLIP / GIT | LLaVA-Instruct-150K-JA, Japanese STAIR Captions, Japanese Visual Genome VQA dataset | Turing | CC BY&#x2011;NC 4.0 | ◯<br>([blip-ja-stablelm-base-7b-v0](https://huggingface.co/turing-motors/heron-chat-blip-ja-stablelm-base-7b-v0), [git-ja-stablelm-base-7b-v0](https://huggingface.co/turing-motors/heron-chat-git-ja-stablelm-base-7b-v0), [git-ELYZA-fast-7b-v0](https://huggingface.co/turing-motors/heron-chat-git-ELYZA-fast-7b-v0)) |
| [Japanese InstructBLIP Alpha](https://stability.ai/blog/announcing-japanese-instructblip-alpha) | InstructBLIP | Japanese CC12M, STAIR Captions, Japanese Visual Genome VQA dataset | Stability AI | [Research license](https://huggingface.co/stabilityai/japanese-instructblip-alpha/blob/main/LICENSE) | [◯](https://huggingface.co/stabilityai/japanese-instructblip-alpha) |
| [Japanese Stable VLM](https://ja.stability.ai/blog/japanese-stable-vlm) | LLaVA-1.5 | Japanese CC12M, STAIR Captions, Japanese Visual Genome VQA dataset | Stability AI | STABILITY AI JAPANESE STABLE VLM COMMUNITY LICENSE | [◯](https://huggingface.co/stabilityai/japanese-stable-vlm) |
| [Heron](https://github.com/turingmotors/heron) | BLIP / GIT | LLaVA-Instruct-150K-JA, Japanese STAIR Captions, Japanese Visual Genome VQA dataset | Turing | CC BY&#x2011;NC 4.0 | ◯<br>([blip-ja-stablelm-base-7b-v0](https://huggingface.co/turing-motors/heron-chat-blip-ja-stablelm-base-7b-v0), [git-ja-stablelm-base-7b-v0](https://huggingface.co/turing-motors/heron-chat-git-ja-stablelm-base-7b-v0), [git-ELYZA-fast-7b-v0](https://huggingface.co/turing-motors/heron-chat-git-ELYZA-fast-7b-v0)) |
| [Japanese InstructBLIP Alpha](https://stability.ai/blog/announcing-japanese-instructblip-alpha) | InstructBLIP | Japanese CC12M, STAIR Captions, Japanese Visual Genome VQA dataset | Stability AI | JAPANESE STABLELM RESEARCH LICENSE | [◯](https://huggingface.co/stabilityai/japanese-instructblip-alpha) |
| [rinna MiniGPT-4](https://rinna.co.jp/news/2023/07/20230731.html)[^11] | MiniGPT-4 | CC12M, COCO 2014, Visual Genome, STAIR Captions, Japanese Visual Genome VQA dataset | rinna | MIT | [◯](https://huggingface.co/rinna/bilingual-gpt-neox-4b-minigpt4) |

<a id="multimodal-others"></a>
Expand Down Expand Up @@ -283,10 +284,12 @@ Please point out any errors on the [issues page](https://github.com/llm-jp/aweso
| BLIP-2 | 2023.01.30 | ICML 2023 | [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://arxiv.org/abs/2301.12597) |
| Llama | 2023.02.27 | - | [LLaMA: Open and Efficient Foundation Language Models](https://arxiv.org/abs/2302.13971) |
| GPT-4 | 2023.03.15 | - | [GPT-4 Technical Report](https://arxiv.org/abs/2303.08774) |
| LLaVA | 2023.04.17 | NeurIPS 2023 | [Visual Instruction Tuning](https://arxiv.org/abs/2304.08485) |
| MiniGPT-4 | 2023.04.20 | - | [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://arxiv.org/abs/2304.10592) |
| InstructBLIP | 2023.05.11 | - | [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://arxiv.org/abs/2305.06500) |
| RWKV | 2023.05.22 | - | [RWKV: Reinventing RNNs for the Transformer Era](https://arxiv.org/abs/2305.13048) |
| Llama 2 | 2023.07.18 | - | [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://arxiv.org/abs/2307.09288) |
| LLaVA-1.5 | 2023.10.05 | - | [Improved Baselines with Visual Instruction Tuning](https://arxiv.org/abs/2310.03744) |

<a id="contributors"></a>
## Our Contributors
Expand Down
7 changes: 5 additions & 2 deletions README_fr.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -209,8 +209,9 @@ N'hésitez pas à signaler les erreurs sur la page [issues](https://github.com/l

| | Architecture | Données d'entraînement | Développeur | Licence | HuggingFace? |
|:---|:---:|:---:|:---:|:---:|:---:|
| [Heron](https://prtimes.jp/main/html/rd/p/000000034.000098132.html) | BLIP / GIT | LLaVA-Instruct-150K-JA, Japanese STAIR Captions, jeu de données Japanese Visual Genome VQA | Turing | CC BY&#x2011;NC 4.0 | ◯<br>([blip-ja-stablelm-base-7b-v0](https://huggingface.co/turing-motors/heron-chat-blip-ja-stablelm-base-7b-v0), [git-ja-stablelm-base-7b-v0](https://huggingface.co/turing-motors/heron-chat-git-ja-stablelm-base-7b-v0), [git-ELYZA-fast-7b-v0](https://huggingface.co/turing-motors/heron-chat-git-ELYZA-fast-7b-v0)) |
| [Japanese InstructBLIP Alpha](https://stability.ai/blog/announcing-japanese-instructblip-alpha) | InstructBLIP | Japanese CC12M, STAIR Captions, jeu de données Japanese Visual Genome VQA | Stability AI | [Research license](https://huggingface.co/stabilityai/japanese-instructblip-alpha/blob/main/LICENSE) | [◯](https://huggingface.co/stabilityai/japanese-instructblip-alpha) |
| [Japanese Stable VLM](https://ja.stability.ai/blog/japanese-stable-vlm) | LLaVA-1.5 | Japanese CC12M, STAIR Captions, jeu de données Japanese Visual Genome VQA | Stability AI | STABILITY AI JAPANESE STABLE VLM COMMUNITY LICENSE | [◯](https://huggingface.co/stabilityai/japanese-stable-vlm) |
| [Heron](https://github.com/turingmotors/heron) | BLIP / GIT | LLaVA-Instruct-150K-JA, Japanese STAIR Captions, jeu de données Japanese Visual Genome VQA | Turing | CC BY&#x2011;NC 4.0 | ◯<br>([blip-ja-stablelm-base-7b-v0](https://huggingface.co/turing-motors/heron-chat-blip-ja-stablelm-base-7b-v0), [git-ja-stablelm-base-7b-v0](https://huggingface.co/turing-motors/heron-chat-git-ja-stablelm-base-7b-v0), [git-ELYZA-fast-7b-v0](https://huggingface.co/turing-motors/heron-chat-git-ELYZA-fast-7b-v0)) |
| [Japanese InstructBLIP Alpha](https://stability.ai/blog/announcing-japanese-instructblip-alpha) | InstructBLIP | Japanese CC12M, STAIR Captions, jeu de données Japanese Visual Genome VQA | Stability AI | JAPANESE STABLELM RESEARCH LICENSE | [◯](https://huggingface.co/stabilityai/japanese-instructblip-alpha) |
| [rinna MiniGPT-4](https://rinna.co.jp/news/2023/07/20230731.html)[^11] | MiniGPT-4 | CC12M, COCO 2014, Visual Genome, STAIR Captions, Japanese Visual Genome VQA dataset | rinna | MIT | [◯](https://huggingface.co/rinna/bilingual-gpt-neox-4b-minigpt4) |

<a id="multimodal-others"></a>
Expand Down Expand Up @@ -283,10 +284,12 @@ N'hésitez pas à signaler les erreurs sur la page [issues](https://github.com/l
| BLIP-2 | 2023.01.30 | ICML 2023 | [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://arxiv.org/abs/2301.12597) |
| Llama | 2023.02.27 | - | [LLaMA: Open and Efficient Foundation Language Models](https://arxiv.org/abs/2302.13971) |
| GPT-4 | 2023.03.15 | - | [GPT-4 Technical Report](https://arxiv.org/abs/2303.08774) |
| LLaVA | 2023.04.17 | NeurIPS 2023 | [Visual Instruction Tuning](https://arxiv.org/abs/2304.08485) |
| MiniGPT-4 | 2023.04.20 | - | [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://arxiv.org/abs/2304.10592) |
| InstructBLIP | 2023.05.11 | - | [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://arxiv.org/abs/2305.06500) |
| RWKV | 2023.05.22 | - | [RWKV: Reinventing RNNs for the Transformer Era](https://arxiv.org/abs/2305.13048) |
| Llama 2 | 2023.07.18 | - | [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://arxiv.org/abs/2307.09288) |
| LLaVA-1.5 | 2023.10.05 | - | [Improved Baselines with Visual Instruction Tuning](https://arxiv.org/abs/2310.03744) |

<a id="contributors"></a>
## Nos contributeurs
Expand Down

0 comments on commit 8b3ae02

Please sign in to comment.