models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
pMistral-7B-Instruct-v0.2Llama3.1-8B-RAFT_PMIX_P80_5DOCS_CoT_A-MEDICAL-Instruct-r64-last-full-epochLlama3.1-8B-RAFT_PMIX_P80_3DOCS_CoT_A-WIKI-Instruct-r64-last-full-epochLlama3.1-8B-RAFT_PMIX_P80_5DOCS_CoT_A-LAW-Instruct-r64-best-eval-lossLlama3.1-8B-RAFT_PMIX_P80_5DOCS_CoT_A-LAW-Instruct-r64-last-full-epochLlama3.1-8B-RAFT_PMIX_P40_3DOCS_CoT_A-LAW-Instruct-r64-best-eval-lossLlama3.1-8B-RAFT_PMIX_P80_3DOCS_CoT_A-LAW-Instruct-r64-last-full-epochLlama3.1-8B-RAFT_PMIX_P40_3DOCS_CoT_A-LAW-Instruct-r64-last-full-epochLlama3.1-8B-RAFT_PMIX_P60_3DOCS_CoT_A-WIKI-Instruct-r64-best-eval-lossLlama3.1-8B-RAFT_PMIX_P60_3DOCS_CoT_A-LAW-Instruct-r64-best-eval-lossLlama3.1-8B-RAFT_PMIX_P60_3DOCS_CoT_A-WIKI-Instruct-r64-last-full-epochtiny-bert-sst2-distilledLlama3.1-8B-RAFT_PMIX_P60_3DOCS_CoT_A-LAW-Instruct-r64-last-full-epochP-Mistral-7BLlama3.1-8B-RAFT_PMIX_P80_3DOCS_CoT_A-WIKI-Instruct-r64-best-eval-lossFalse_large_pmi_para0_sent1_span2_itFalse_ssoftmax_rrFalse_8_1024_0.15_1gpt2-base-v1Llama3.1-8B-RAFT_PMIX_P80_3DOCS_CoT_A-MEDICAL-Instruct-r64-best-eval-lossLlama3.1-8B-RAFT_PMIX_P60_3DOCS_CoT_A-MEDICAL-Instruct-r64-last-full-epochLlama3.1-8B-RAFT_PMIX_P40_3DOCS_CoT_A-MEDICAL-Instruct-r64-last-full-epochLlama3.1-8B-RAFT_PMIX_P40_3DOCS_CoT_A-WIKI-Instruct-r64-last-full-epochLlama3.1-8B-RAFT_PMIX_P80_5DOCS_CoT_A-MEDICAL-Instruct-r64-best-eval-loss7b_pmistral_v01_sftepoch2Llama3.1-8B-RAFT_PMIX_P80_3DOCS_CoT_A-LAW-Instruct-r64-best-eval-lossLlama3.1-8B-RAFT_PMIX_P80_3DOCS_CoT_A-MEDICAL-Instruct-r64-last-full-epochLlama3.1-8B-RAFT_PMIX_P60_3DOCS_CoT_A-MEDICAL-Instruct-r64-best-eval-lossFalse_large_pmi_para0_sent1_span2_itTrue_sargmax_rrFalse_8_1024_0.15_1False_large_pmi_para0_sent1_span2_itFalse_sargmax_rrFalse_8_1024_0.15_1False_large_pmi_para0_sent1_span2_itTrue_sargmax_rrFalse_8_1024_0.3_epoch1False_large_pmi_para0_sent1_span2_itTrue_sargmax_rrFalse_7_1024_0.3_seed1_epoch1