AI Agent Hub

LLM Models · tokyotech-llm

Browse the world's large language models. Compare parameters, benchmarks, VRAM and more.

61 models from tokyotech-llm Compare
GPT-OSS-Swallow-120B-SFT-v0.1 logo
GPT-OSS-Swallow-120B-SFT-v0.1
tokyotech-llm

GPT-OSS-Swallow v0.1 is a family of large language models available in 20B and 120B parameter sizes. Built as bilingual Japanese-English models, they were developed through Continual Pre-Training (CPT), Supervised Fine-Tuning (SFT), and Reinforcement Learning with Verifiable Rewa…

open-source 120.0B ↓ 140
Swallow-13b-instruct-hf logo
Swallow-13b-instruct-hf
tokyotech-llm

Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data. The tuned versions use supervised fine-tuning (SFT). Links to other models can be found in the index.

open-source 13.0B ↓ 133
Swallow-70b-instruct-hf logo
Swallow-70b-instruct-hf
tokyotech-llm

Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data. The tuned versions use supervised fine-tuning (SFT). Links to other models can be found in the index.

open-source 70.0B ↓ 121
Swallow-13b-instruct-v0.1 logo
Swallow-13b-instruct-v0.1
tokyotech-llm

Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data. The tuned versions use supervised fine-tuning (SFT). Links to other models can be found in the index.

open-source 13.0B ↓ 119
Llama-3-Swallow-8B-v0.1 logo
Llama-3-Swallow-8B-v0.1
tokyotech-llm

Llama3 Swallow - Built with Meta Llama 3

open-source 8.0B ↓ 118
Gemma-2-Llama-Swallow-2b-pt-v0.1 logo
Gemma-2-Llama-Swallow-2b-pt-v0.1
tokyotech-llm

Gemma-2-Llama-Swallow series was built by continual pre-training on the gemma-2 models. Gemma 2 Swallow enhanced the Japanese language capabilities of the original Gemma 2 while retaining the English language capabilities. We use approximately 200 billion tokens that were sampled…

open-source 2.0B ↓ 114
Swallow-7b-instruct-v0.1 logo
Swallow-7b-instruct-v0.1
tokyotech-llm

Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data. The tuned versions use supervised fine-tuning (SFT). Links to other models can be found in the index.

open-source 7.0B ↓ 112
Llama-3.1-Swallow-8B-v0.2 logo
Llama-3.1-Swallow-8B-v0.2
tokyotech-llm

Llama 3.1 Swallow is a series of large language models (8B, 70B) that were built by continual pre-training on the Meta Llama 3.1 models. Llama 3.1 Swallow enhanced the Japanese language capabilities of the original Llama 3.1 while retaining the English language capabilities. We u…

open-source 8.0B ↓ 108
Swallow-MS-7b-instruct-v0.1 logo
Swallow-MS-7b-instruct-v0.1
tokyotech-llm

Our Swallow-MS-7b-v0.1 model has undergone continual pre-training from the Mistral-7B-v0.1, primarily with the addition of Japanese language data.

open-source 7.0B ↓ 106
Swallow-MS-7b-v0.1 logo
Swallow-MS-7b-v0.1
tokyotech-llm

Our Swallow-MS-7b-v0.1 model has undergone continual pre-training from the Mistral-7B-v0.1, primarily with the addition of Japanese language data.

open-source 7.0B ↓ 97
Swallow-70b-NVE-hf logo
Swallow-70b-NVE-hf
tokyotech-llm

Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data. The tuned versions use supervised fine-tuning (SFT). Links to other models can be found in the index.

open-source 70.0B ↓ 83
Llama-3.1-Swallow-70B-Instruct-v0.1 logo
Llama-3.1-Swallow-70B-Instruct-v0.1
tokyotech-llm

Llama 3.1 Swallow is a series of large language models (8B, 70B) that were built by continual pre-training on the Meta Llama 3.1 models. Llama 3.1 Swallow enhanced the Japanese language capabilities of the original Llama 3.1 while retaining the English language capabilities. We u…

open-source 70.0B ↓ 81