Open Models, Ready for Production

Featured Models

All Models

64,997 results found

All Product Options, Modalities, and Model Types

Model Name	Input	Output	Type
PrunaAI Orenguteng-Llama-3-8B-LexiFun-Uncensored-V1-bnb-4bit-smashed			Quantized	Deploy
PrunaAI DiscoResearch-Llama3-German-8B-AWQ-4bit-smashed			Quantized	Deploy
PrunaAI DiscoResearch-Llama3-German-8B-bnb-8bit-smashed			Quantized	Deploy
PrunaAI DiscoResearch-Llama3-German-8B-bnb-4bit-smashed			Quantized	Deploy
gohsyi Llama-3-8b-rlhf-iter3-v0.1			Base	Deploy
XiShi5941 llama-3-8b-unsafe20240715192920			Base	Deploy
kaping llama-3-assistace			Base	Deploy
martimfasantos tinyllama-1.1b-mt-simpo_beta2.0_gamma1.6_LR1e-7_BS32_rmsprop_3epochs_compare			Fine-tuned	Deploy
guchia MM_adapter2_Meta-Llama-3-8B-Instruct_0.11			Base	Deploy
sehe1121 Llama-3-BCCard-Kor-8B			Base	Deploy
guchia MM_adapter2_Meta-Llama-3-8B-Instruct_0.21			Base	Deploy
guchia MM_adapter2_Meta-Llama-3-8B-Instruct_0.31			Base	Deploy
gohsyi Llama-3-8b-rlhf-iter2-v0.1			Base	Deploy
gohsyi Llama-3-8b-rlhf-iter1-v0.1			Base	Deploy
gohsyi Llama-3-8b-rlhf-iter1-reweighted-v0.1			Base	Deploy
ehristoforu Llama3-8B-Instruct-pruned			Fine-tuned	Deploy
gohsyi Llama-3-8b-rlhf-iter1-threshold-v0.1			Base	Deploy
PrunaAI BEE-spoke-data-smol_llama-220M-GQA-AWQ-4bit-smashed			Quantized	Deploy
PrunaAI BEE-spoke-data-smol_llama-220M-GQA-bnb-4bit-smashed			Quantized	Deploy
zorache llama3_repnoise_full_alpha-1.0_beta-0.001_lr-5e-05_batch-4_epoch-0.5			Base	Deploy
zorache llama3_repnoise_full_alpha-1.0_beta-0.001_lr-5e-05_batch-4_epoch-1			Base	Deploy
zorache llama3_repnoise_full_alpha-1.0_beta-0.001_lr-5e-05_batch-4_epoch-1.5			Base	Deploy
zorache llama3_repnoise_full_alpha-1.0_beta-0.001_lr-5e-05_batch-4_epoch-2			Base	Deploy
zorache llama3_repnoise_full_alpha-1.0_beta-0.0001_lr-5e-05_batch-4_epoch-0.5			Base	Deploy
zorache llama3_repnoise_full_alpha-1.0_beta-0.0001_lr-5e-05_batch-4_epoch-1			Base	Deploy
zorache llama3_repnoise_full_alpha-1.0_beta-0.0001_lr-5e-05_batch-4_epoch-1.5			Base	Deploy
zorache llama3_repnoise_full_alpha-1.0_beta-0.0001_lr-5e-05_batch-4_epoch-2			Base	Deploy
PrunaAI vonjack-Phi-3-mini-4k-instruct-LLaMAfied-AWQ-4bit-smashed			Quantized	Deploy
zorache llama3_rmu_layer-5-6-7_alpha-100_steer-20_lr-5e-05_batch-4_epoch-0.5			Base	Deploy
zorache llama3_rmu_layer-5-6-7_alpha-100_steer-20_lr-5e-05_batch-4_epoch-1			Base	Deploy
guchia MM_adapter2_Meta-Llama-3-8B-Instruct_0.41			Base	Deploy
zorache llama3_rmu_layer-5-6-7_alpha-100_steer-20_lr-5e-05_batch-4_epoch-1.5			Base	Deploy
zorache llama3_rmu_layer-5-6-7_alpha-100_steer-20_lr-5e-05_batch-4_epoch-2			Base	Deploy
PrunaAI vonjack-Phi-3-mini-4k-instruct-LLaMAfied-bnb-4bit-smashed			Quantized	Deploy
radi-cho Meta-Llama-3-70B-FLUTE			Base	Deploy
radi-cho Meta-Llama-3-8B-FLUTE			Base	Deploy
zorache llama3_rmu_layer-5-6-7_alpha-50_steer-20_lr-5e-05_batch-4_epoch-0.5			Base	Deploy
zorache llama3_rmu_layer-5-6-7_alpha-50_steer-20_lr-5e-05_batch-4_epoch-1			Base	Deploy
zorache llama3_rmu_layer-5-6-7_alpha-50_steer-20_lr-5e-05_batch-4_epoch-1.5			Base	Deploy
zorache llama3_rmu_layer-5-6-7_alpha-50_steer-20_lr-5e-05_batch-4_epoch-2			Base	Deploy
ehristoforu MyLlama-8b			Merged	Deploy
PrunaAI Locutusque-Llama-3-Hercules-5.0-8B-bnb-4bit-smashed			Quantized	Deploy