Taishi

Taishi-N324's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in llm-jp/optimal-sparsity-math-d512-E32-k2-920M-A170M 4 months ago

Improve model card: Add metadata, paper abstract, and GitHub link

#1 opened 4 months ago by

nielsr

New activity in llm-jp/optimal-sparsity-math-d512-E16-k2-520M-A170M 4 months ago

Improve model card: Add metadata, paper link, code link, and description

❤️ 1

#1 opened 4 months ago by

nielsr

New activity in llm-jp/optimal-sparsity-math-d512-E8-k2-320M-A170M 4 months ago

Add model card

❤️ 1

#1 opened 4 months ago by

nielsr

commented a paper 4 months ago

Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks

Paper • 2508.18672 • Published Aug 26, 2025 • 10 •

2

commented a paper 10 months ago

Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization

Paper • 2502.19261 • Published Feb 26, 2025 • 6 •

3

New activity in tokyotech-llm/Swallow-7b-NVE-hf 12 months ago

Adding `safetensors` variant of this model

#2 opened 12 months ago by

SFconvertbot

New activity in tokyotech-llm/Llama-3.1-Swallow-70B-Instruct-v0.1 about 1 year ago

Is the license "gemma"?

2

#1 opened about 1 year ago by

torotoki

New activity in tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1 about 1 year ago

Any suggestions on system prompt?

2

#2 opened over 1 year ago by

conan1024hao

New activity in tokyotech-llm/Swallow-7b-hf over 1 year ago

Adding `safetensors` variant of this model

#1 opened almost 2 years ago by

SFconvertbot

New activity in tokyotech-llm/Swallow-7b-instruct-v0.1 over 1 year ago

Delete tokenizer.json

#2 opened over 1 year ago by

Taishi-N324

New activity in tokyotech-llm/Llama-3-Swallow-70B-Instruct-v0.1 over 1 year ago

Add `<|eot_id|>` token (id: 128009) to `eos_token_id`

1

#1 opened over 1 year ago by

junya-takayama

New activity in tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1 over 1 year ago

Add `<|eot_id|>` token (id: 128009) to `eos_token_id`

1

#1 opened over 1 year ago by

junya-takayama

New activity in tokyotech-llm/Swallow-7b-hf over 1 year ago

model読み込み時のtorch_dtype, device_map設定

1

#2 opened almost 2 years ago by

kanhatakeyama

New activity in tokyotech-llm/Swallow-70b-instruct-hf over 1 year ago

Chat/instruction template

1

#2 opened over 1 year ago by

Gnurro2

New activity in tokyotech-llm/Swallow-7b-instruct-v0.1 over 1 year ago

Typo in the system prompt example?

2

#1 opened over 1 year ago by

yumemio

New activity in tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1 over 1 year ago

torch_dtype=torch.bfloat16, device_map="auto"

❤️ 1

#2 opened almost 2 years ago by

kanhatakeyama

New activity in tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1 almost 2 years ago

Update README.md (add a link to Mixtral)

#1 opened almost 2 years ago by

nss-ysasaki

New activity in tokyotech-llm/Swallow-MS-7b-v0.1 almost 2 years ago

Update README.md (add a link to Mistral)

#1 opened almost 2 years ago by

nss-ysasaki

New activity in tokyotech-llm/Swallow-7b-instruct-hf about 2 years ago

Here is the article in Japanese and the code that works with Google Colab Pro | 日本語の解説記事と Google Colab Pro で動くコードです

❤️ 2

1

#1 opened about 2 years ago by

AICUaki

New activity in tokyotech-llm/Swallow-13b-instruct-hf about 2 years ago

Not found requirements.txt

2

#1 opened about 2 years ago by

alfredplpl