The tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.1 galaxy

10 models are built on tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.1: 5 quantized, 1 fine-tuned, 2 adapters and 2 merges. Together they were downloaded 1,495 times in the last 30 days.

Most downloaded direct derivatives

• featherless-ai-quants/tokyotech-llm-Llama-3.1-Swallow-8B-Instruct-v0.1-GGUF (quantized), 395 downloads in 30 days
• mlx-community/Llama-3.1-Swallow-8B-Instruct-v0.1 (finetune), 81 downloads in 30 days
• mlx-community/Llama-3.1-Swallow-8B-Instruct-v0.1-4bit (quantized), 32 downloads in 30 days
• AELLM/llama-3.1-swallow-hermes-8b-v0.1 (merge), 29 downloads in 30 days
• mlx-community/Llama-3.1-Swallow-8B-Instruct-v0.1-8bit (quantized), 27 downloads in 30 days
• AELLM/llama-3.1-swallow-gen-8b-v0.1 (merge), 21 downloads in 30 days
• yf591/llama3-8b-rag-sft-lora-v1 (adapter), 10 downloads in 30 days
• yf591/Llama3SW8B_it_v0.1_qlora_FukuyamaBen (adapter), 5 downloads in 30 days

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