The tokyotech-llm/Llama-3.1-Swallow-8B-v0.2 galaxy

11 models are built on tokyotech-llm/Llama-3.1-Swallow-8B-v0.2: 3 quantized, 2 fine-tuned, 0 adapters and 6 merges. Together they were downloaded 1,973 times in the last 30 days.

Most downloaded direct derivatives

• mradermacher/Llama-3.1-Swallow-8B-v0.2-i1-GGUF (quantized), 1K downloads in 30 days
• mradermacher/Llama-3.1-Swallow-8B-v0.2-GGUF (quantized), 506 downloads in 30 days
• tensorblock/Llama-3.1-Swallow-8B-v0.2-GGUF (quantized), 94 downloads in 30 days
• HachiML/Llama-3.1-Swallow-8B-v0.2-reasoningvector-deepseek-r1 (finetune), 24 downloads in 30 days
• mergekit-community/mergekit-della_linear-uogzotg (merge), 11 downloads in 30 days
• globalyako/swallowv2-8b-ft-jp-r64_grpo-merged (finetune), 8 downloads in 30 days

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.