The Rakuten/RakutenAI-7B-instruct galaxy
14 models are built on Rakuten/RakutenAI-7B-instruct: 11 quantized, 1 fine-tuned, 0 adapters and 2 merges. Together they were downloaded 1,541 times in the last 30 days.
Most downloaded direct derivatives
- mradermacher/RakutenAI-7B-instruct-GGUF (quantized), 768 downloads in 30 days
- mradermacher/RakutenAI-7B-instruct-i1-GGUF (quantized), 277 downloads in 30 days
- tensorblock/RakutenAI-7B-instruct-GGUF (quantized), 73 downloads in 30 days
- sakaltcommunity/sakaltum-7b (merge), 37 downloads in 30 days
- mlx-community/RakutenAI-7B-instruct-MLX-8bit (quantized), 33 downloads in 30 days
- mlx-community/RakutenAI-7B-instruct-MLX-4bit (quantized), 31 downloads in 30 days
- keisuke-miyako/RakutenAI-7B-instruct-gguf-q4_k_m (quantized), 26 downloads in 30 days
- AmpereComputing/rakutenai-7b-instruct-gguf (quantized), 15 downloads in 30 days
- keisuke-miyako/RakutenAI-7B-instruct-ct2-int8 (finetune), 8 downloads in 30 days
- geninhu/RakutenAI-7B-instruct-GPTQ (quantized), 7 downloads in 30 days
- keisuke-miyako/RakutenAI-7B-instruct-onnx-int4 (quantized), 7 downloads in 30 days
- Urban-L/RevotenJLM-7B-slerp (merge), 6 downloads in 30 days
- ultragtx/RakutenAI-7B-instruct-Q4_K_M-GGUF (quantized), 2 downloads in 30 days
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.