-
rinna/qwen2.5-bakeneko-32b
Text Generation β’ 33B β’ Updated β’ 12 β’ β’ 7 -
rinna/gemma-2-baku-2b
Text Generation β’ 3B β’ Updated β’ 109 β’ β’ 7 -
rinna/llama-3-youko-70b
Text Generation β’ 71B β’ Updated β’ 10 β’ 3 -
rinna/llama-3-youko-8b
Text Generation β’ 8B β’ Updated β’ 298 β’ β’ 62
rinna Co., Ltd.
company
Verified
AI & ML interests
Generative AI
The bakeneko model series are based on the qwen2.5 series and have been continually pre-trained on Japanese-specific corpora.
-
rinna/qwen2.5-bakeneko-32b
Text Generation β’ 33B β’ Updated β’ 12 β’ β’ 7 -
rinna/qwen2.5-bakeneko-32b-instruct
Text Generation β’ 33B β’ Updated β’ 603 β’ β’ 7 -
rinna/qwen2.5-bakeneko-32b-instruct-awq
Text Generation β’ 33B β’ Updated β’ 9 -
rinna/qwen2.5-bakeneko-32b-instruct-gguf
Text Generation β’ 33B β’ Updated β’ 75 β’ 2
The youko model series are based on the llama-3 series and have been continually pre-trained on Japanese-specific corpora.
-
rinna/llama-3-youko-70b
Text Generation β’ 71B β’ Updated β’ 10 β’ 3 -
rinna/llama-3-youko-70b-gptq
Text Generation β’ 71B β’ Updated β’ 8 -
rinna/llama-3-youko-70b-instruct
Text Generation β’ 71B β’ Updated β’ 506 β’ β’ 1 -
rinna/llama-3-youko-70b-instruct-gptq
Text Generation β’ 71B β’ Updated β’ 11
The youri model series are based on the llama-2 series and have been continually pre-trained on Japanese-specific corpora.
The japanese-gpt-neox-3.6b series are pre-trained from scratch on Japanese corpora.
-
rinna/bilingual-gpt-neox-4b-minigpt4
Image-Text-to-Text β’ Updated β’ 17 -
rinna/japanese-stable-diffusion
Text-to-Image β’ Updated β’ 10 β’ 178 -
rinna/japanese-cloob-vit-b-16
Feature Extraction β’ 0.2B β’ Updated β’ 53 β’ 13 -
rinna/japanese-clip-vit-b-16
Feature Extraction β’ 0.2B β’ Updated β’ 39.3k β’ 24
The baku model series are based on the gemma-2 series and have been continually pre-trained on Japanese-specific corpora.
The nekomata model series are based on the qwen series and have been continually pre-trained on Japanese-specific corpora.
-
rinna/nekomata-14b
Text Generation β’ 14B β’ Updated β’ 1.17k β’ 19 -
rinna/nekomata-14b-gguf
Text Generation β’ 14B β’ Updated β’ 8 β’ 3 -
rinna/nekomata-14b-instruction
Text Generation β’ 14B β’ Updated β’ 36 β’ 23 -
rinna/nekomata-14b-instruction-gguf
Text Generation β’ 14B β’ Updated β’ 28 β’ 12
The bilingual-gpt-neox-4b series are pre-trained from scratch on a mixture of Japanese and English corpora.
-
rinna/bilingual-gpt-neox-4b
Text Generation β’ 4B β’ Updated β’ 2.34k β’ 28 -
rinna/bilingual-gpt-neox-4b-8k
Text Generation β’ 4B β’ Updated β’ 14 β’ 22 -
rinna/bilingual-gpt-neox-4b-instruction-sft
Text Generation β’ 4B β’ Updated β’ 1.25k β’ 17 -
rinna/bilingual-gpt-neox-4b-instruction-ppo
Text Generation β’ 4B β’ Updated β’ 78 β’ 14
-
rinna/qwen2.5-bakeneko-32b
Text Generation β’ 33B β’ Updated β’ 12 β’ β’ 7 -
rinna/gemma-2-baku-2b
Text Generation β’ 3B β’ Updated β’ 109 β’ β’ 7 -
rinna/llama-3-youko-70b
Text Generation β’ 71B β’ Updated β’ 10 β’ 3 -
rinna/llama-3-youko-8b
Text Generation β’ 8B β’ Updated β’ 298 β’ β’ 62
-
rinna/bilingual-gpt-neox-4b-minigpt4
Image-Text-to-Text β’ Updated β’ 17 -
rinna/japanese-stable-diffusion
Text-to-Image β’ Updated β’ 10 β’ 178 -
rinna/japanese-cloob-vit-b-16
Feature Extraction β’ 0.2B β’ Updated β’ 53 β’ 13 -
rinna/japanese-clip-vit-b-16
Feature Extraction β’ 0.2B β’ Updated β’ 39.3k β’ 24
The bakeneko model series are based on the qwen2.5 series and have been continually pre-trained on Japanese-specific corpora.
-
rinna/qwen2.5-bakeneko-32b
Text Generation β’ 33B β’ Updated β’ 12 β’ β’ 7 -
rinna/qwen2.5-bakeneko-32b-instruct
Text Generation β’ 33B β’ Updated β’ 603 β’ β’ 7 -
rinna/qwen2.5-bakeneko-32b-instruct-awq
Text Generation β’ 33B β’ Updated β’ 9 -
rinna/qwen2.5-bakeneko-32b-instruct-gguf
Text Generation β’ 33B β’ Updated β’ 75 β’ 2
The baku model series are based on the gemma-2 series and have been continually pre-trained on Japanese-specific corpora.
The youko model series are based on the llama-3 series and have been continually pre-trained on Japanese-specific corpora.
-
rinna/llama-3-youko-70b
Text Generation β’ 71B β’ Updated β’ 10 β’ 3 -
rinna/llama-3-youko-70b-gptq
Text Generation β’ 71B β’ Updated β’ 8 -
rinna/llama-3-youko-70b-instruct
Text Generation β’ 71B β’ Updated β’ 506 β’ β’ 1 -
rinna/llama-3-youko-70b-instruct-gptq
Text Generation β’ 71B β’ Updated β’ 11
The nekomata model series are based on the qwen series and have been continually pre-trained on Japanese-specific corpora.
-
rinna/nekomata-14b
Text Generation β’ 14B β’ Updated β’ 1.17k β’ 19 -
rinna/nekomata-14b-gguf
Text Generation β’ 14B β’ Updated β’ 8 β’ 3 -
rinna/nekomata-14b-instruction
Text Generation β’ 14B β’ Updated β’ 36 β’ 23 -
rinna/nekomata-14b-instruction-gguf
Text Generation β’ 14B β’ Updated β’ 28 β’ 12
The youri model series are based on the llama-2 series and have been continually pre-trained on Japanese-specific corpora.
The bilingual-gpt-neox-4b series are pre-trained from scratch on a mixture of Japanese and English corpora.
-
rinna/bilingual-gpt-neox-4b
Text Generation β’ 4B β’ Updated β’ 2.34k β’ 28 -
rinna/bilingual-gpt-neox-4b-8k
Text Generation β’ 4B β’ Updated β’ 14 β’ 22 -
rinna/bilingual-gpt-neox-4b-instruction-sft
Text Generation β’ 4B β’ Updated β’ 1.25k β’ 17 -
rinna/bilingual-gpt-neox-4b-instruction-ppo
Text Generation β’ 4B β’ Updated β’ 78 β’ 14
The japanese-gpt-neox-3.6b series are pre-trained from scratch on Japanese corpora.