mlfoundations-dev/oh_v1.2_opengpt_x2
8B
•
Updated
•
3
mlfoundations-dev/oh_v1.2_opengpt_x.125
8B
•
Updated
•
4
mlfoundations-dev/oh_v1.2_opengpt_x.5
8B
•
Updated
•
4
mlfoundations-dev/oh_v1.2_opengpt_x.25
8B
•
Updated
•
4
mlfoundations-dev/oh_v1.2_alpaca_x4
Updated
mlfoundations-dev/oh_v1.2_alpaca_x.5
Updated
mlfoundations-dev/oh_v1.2_alpaca_x2
Updated
mlfoundations-dev/oh_v1.2_alpaca_x.25
Updated
mlfoundations-dev/hp_ablations_qwen_scheduler_linear_warmup0.10_dcftv1.2
Text Generation
•
8B
•
Updated
•
6
mlfoundations-dev/hp_ablations_qwen_scheduler_cosine_warmup0.10_minlr5e-7_dcftv1.2
Text Generation
•
8B
•
Updated
•
5
mlfoundations-dev/hp_ablations_qwen_scheduler_linear_warmup0.05_dcftv1.2
Text Generation
•
8B
•
Updated
•
4
mlfoundations-dev/hp_ablations_qwen_adambeta1_0.85_dcftv1.2
Text Generation
•
8B
•
Updated
•
3
mlfoundations-dev/hp_ablations_qwen_scheduler_cosine_warmup0.05_minlr1e-7_dcftv1.2
Text Generation
•
8B
•
Updated
•
5
mlfoundations-dev/hp_ablations_qwen_adambeta2_0.95_dcftv1.2
Text Generation
•
8B
•
Updated
•
6
mlfoundations-dev/hp_ablations_qwen_adambeta1_0.9_dcftv1.2
Text Generation
•
8B
•
Updated
•
6
mlfoundations-dev/hp_ablations_qwen_lr5e-6_dcftv1.2
Text Generation
•
8B
•
Updated
•
3
mlfoundations-dev/hp_ablations_qwen_scheduler_cosine_warmup0.05_dcftv1.2
Text Generation
•
8B
•
Updated
•
4
mlfoundations-dev/hp_ablations_qwen_scheduler_cosine_warmup0.10_dcftv1.2
Text Generation
•
8B
•
Updated
•
6
mlfoundations-dev/hp_ablations_qwen_adambeta2_0.9995_dcftv1.2
Text Generation
•
8B
•
Updated
•
4
mlfoundations-dev/hp_ablations_qwen_scheduler_cosine_warmup0.05_minlr5e-7_dcftv1.2
Text Generation
•
8B
•
Updated
•
4
mlfoundations-dev/hp_ablations_qwen_lr1e-6_dcftv1.2
Text Generation
•
8B
•
Updated
•
4
mlfoundations-dev/hp_ablations_qwen_bsz512_dcftv1.2
Text Generation
•
8B
•
Updated
•
4
mlfoundations-dev/hp_ablations_qwen_lr2e-6_dcftv1.2
Text Generation
•
8B
•
Updated
•
5
mlfoundations-dev/hp_ablations_qwen_scheduler_cosine_warmup0.05_minlr1e-6_dcftv1.2
Text Generation
•
8B
•
Updated
•
6
mlfoundations-dev/hp_ablations_qwen_bsz256_dcftv1.2
Text Generation
•
8B
•
Updated
•
4
mlfoundations-dev/hp_ablations_qwen_scheduler_inverse_sqrt_dcftv1.2
Text Generation
•
8B
•
Updated
•
5
mlfoundations-dev/hp_ablations_qwen_adambeta1_0.95_dcftv1.2
Text Generation
•
8B
•
Updated
•
5
mlfoundations-dev/hp_ablations_qwen_adambeta2_0.995_dcftv1.2
Text Generation
•
8B
•
Updated
•
4
mlfoundations-dev/hp_ablations_qwen_lr1e-5_dcftv1.2
Text Generation
•
8B
•
Updated
•
4
mlfoundations-dev/hp_ablations_qwen_scheduler_cosine_warmup0.15_dcftv1.2
Text Generation
•
8B
•
Updated
•
6