The HuggingFaceH4/mistral-7b-sft-beta galaxy
478 models are built on HuggingFaceH4/mistral-7b-sft-beta: 10 quantized, 454 fine-tuned, 14 adapters and 0 merges. Together they were downloaded 9,822 times in the last 30 days.
Most downloaded direct derivatives
- MaziyarPanahi/mistral-7b-sft-beta-GGUF (quantized), 876 downloads in 30 days
- mradermacher/mistral-7b-sft-beta-i1-GGUF (quantized), 695 downloads in 30 days
- mradermacher/mistral-7b-sft-beta-GGUF (quantized), 170 downloads in 30 days
- ShenaoZhang/0.001_idpo_iter_1 (finetune), 55 downloads in 30 days
- ShenaoZhang/0.001_idpo_noreplacerej_iter_1 (finetune), 52 downloads in 30 days
- cleanrl/ppo_zephyr310 (finetune), 33 downloads in 30 days
- Uppaal/Mistral-sft-ProFS-safety (finetune), 27 downloads in 30 days
- Mihaiii/Metis-0.1 (finetune), 22 downloads in 30 days
- ShenaoZ/0.0001_ablation_iter_1 (finetune), 21 downloads in 30 days
- ShenaoZhang/0.001_zephyr_5551_4iters_bs256_iter_1 (finetune), 21 downloads in 30 days
- Uppaal/Mistral-sft-ProFS-toxicity (finetune), 21 downloads in 30 days
- vwxyzjn/ppo_zephyr1 (finetune), 20 downloads in 30 days
- ShenaoZ/0.01_ablation_4iters_bs256_nodpo_iter_1 (finetune), 19 downloads in 30 days
- ShenaoZhang/0.0001_zephyr_5551_4iters_bs256_iter_1 (finetune), 19 downloads in 30 days
- TTTXXX01/DPO-Zephyr-7B (finetune), 19 downloads in 30 days
- ShenaoZ/0.0_ablation_6iters_iter_1 (finetune), 18 downloads in 30 days
- ShenaoZ/DPO-Zephyr-7B (finetune), 18 downloads in 30 days
- ShenaoZhang/0.0001_3iters_bs256_nodpo_full6w_iter_1 (finetune), 18 downloads in 30 days
- ShenaoZhang/0.001_ablation_4iters_bs128_nodpo_iter_1 (finetune), 18 downloads in 30 days
- ShenaoZhang/0.0_zephyr_5551_4iters_bs256_iter_1 (finetune), 18 downloads in 30 days
- tongliuphysics/Mistral-7B-Base-SFT-FocalPO (finetune), 18 downloads in 30 days
- ShenaoZ/0.0001_ablation_4iters_bs256_iter_1 (finetune), 17 downloads in 30 days
- ShenaoZ/0.001_3iters_bs128_declr_nodpo_useresponse_iter_1 (finetune), 17 downloads in 30 days
- ShenaoZ/0.001_ablation_iter_1 (finetune), 17 downloads in 30 days
- ShenaoZ/0.001_sft_nodpo_3iters_bs256_531lr_iter_1 (finetune), 17 downloads in 30 days