Llama3 Swallow is a Japanese‑enhanced Meta Llama 3 family released July 1 2024, offering 8B and 70B variants in Instruct and chat forms fine‑tuned with SFT and Chat Vector on Megatron‑LM, and benchmarked on key Japanese NLP tasks.
Description in other languages
Statistics
Statistics as of Nov 16, 2026
Hugging Face downloads (last 30 days)
9,000
Hugging Face likes
21
Listed
Jul 5, 2024
Downloads (30-day window) over time
Show as a table
| Month | DL (30d) |
|---|---|
| Dec 2025 | 9,000 |
| Jan 2026 | 9,000 |
| Feb 2026 | 21,000 |
| Mar 2026 | 10,000 |
| Apr 2026 | 9,000 |
| May 2026 | 11,000 |
| Jun 2026 | 9,000 |
| Jul 2026 | 8,000 |
| Aug 2026 | 9,000 |
| Sep 2026 | 9,000 |
| Oct 2026 | 9,000 |
| Nov 2026 | 9,000 |
Downloads over the 30 days before the last snapshot of each month.
Popular in the same category
- japanese-gpt-neox-smallrinna656kA 12‑layer, 768‑hidden Japanese GPT‑NeoX model trained on CC‑100, C4, and Wikipedia, compatible with Huggingface, with an optional toy prefix‑tuning weight that forces each sentence to end with a smiling‑face emoji.
- Spark-X2.5-4B-Heretic-jp-ggufsoyaakinohara589kJapanese‑adapted Spark‑X2.5‑4B model (Heretic JP) with refusal attenuation, pretraining, instruction tuning and tool‑calling repair, available in GGUF quantizations from BF16 to Q4_K_M (~2.5 GiB), usable via llama.cpp for 1,048,576‑token context.
- llm-jp-4-33b-thinking-ggufllm-jp271kLLM‑jp‑4‑33b‑thinking‑gguf is a 33 B Japanese language model from the National Institute of Informatics, pre‑trained with SFT and DPO (no RL), available for llama.cpp via an LLM‑jp fork, and includes detailed usage instructions in its cookbook.
- llm-jp-4.1-8b-thinkingllm-jp80kLLM‑jp‑4.1‑8b‑thinking is a 33 B transformer language model from NII’s LLM R&D Center, pre‑trained with mid‑training only and aligned via SFT/DPO (no RL), designed for Japanese NLP tasks and documented in a cookbook and technical blog.
- llm-jp-3-150mllm-jp75kLLM‑jp‑3‑150m—a 150‑M‑parameter Japanese language model from the National Institute of Informatics’ LLM R&D Center—is distributed in Hugging Face Transformers format, requiring torch ≥ 2.3.0, transformers ≥ 4.40.1, accelerate ≥ 0.29.3, flash‑attn ≥ 2.5.8, and was pretrained on Japanese Wikipedia, Common Crawl, WARP/PDF, WARP/HTML, and Kaken data using a unigram byte‑fallback tokenizer.
- llm-jp-4-8b-instructllm-jp49kllm‑jp‑4‑8b‑instruct is a 4.1 B‑parameter Japanese LLM from NII’s LLM‑jp‑4 series, pretrained on large corpora and then fine‑tuned solely with supervised instruction data (no DPO/REINFORCE) and accompanied by cookbook‑style usage guides and a byte‑fallback unigram tokenizer.
Resources in similar research fields
- Llama-3-70B-japanese-suzume-vector-v0.1mmnga9kExperimental Japanese model created by extracting differences between lightblue/suzume‑llama‑3‑8B‑japanese and Meta‑Llama‑3‑8B‑Instruct using a chat‑vector approach, upsampled and applied to Meta‑Llama‑3‑70B‑Instruct, showing little change and planning future scaling.Shared: Representation Learning・Language Models
- llm-jp-3-1.8bllm-jp3kA collection of Japanese large‑language models (1.8 b to 172 b beta1, with instruct variants) from NII’s R&D Center, packaged in Hugging Face Transformers format and pretrained on a mix of Japanese, English, and Web corpora totalling >1 trillion tokens, requiring torch ≥ 2.3, transformers ≥ 4.40, accelerate ≥ 0.29, and flash‑attn ≥ 2.5.Shared: Language Models・Semantic Text Processing
- japanese-gpt-1brinna2kA 1.3‑B‑parameter, 24‑layer transformer GPT‑1B, trained on Japanese C4, CC‑100, and Wikipedia, was released by rinna Co. on January 26 2022 and is available under the MIT license.Shared: Language Models・Semantic Text Processing
- gpt-neox-japanese-2.7babeja3kA 2.7‑B‑parameter Japanese GPT‑NeoX model trained on Japanese CC‑100 and OSCAR by ABEJA Inc, usable via Hugging Face Transformers pipelines or PyTorch and released under the MIT license.Shared: Language Models・Semantic Text Processing
AISisterAIChanmanju-summoner29This is a Siro Ghost equipped with ChatGPT3.5, called "AI Imouto Aichan". A separate ChatGPT API key is required to use it.GitHubShared: Language Models・Semantic Text Processing
text-generationdiscus043419Easy-to-use scripts to fine-tune GPT-2-JA with your own texts, to generate sentences, and to tweet them automatically.GitHubShared: Language Models・Semantic Text Processing