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.
tt-x4_temperature-t1p0-45-30Btt-x4_temperature-t0p7-45-30Blm-1.3B-select_30B_tokens_by-required_expertise-sample_with_temperature1.0lm-1.3B-select_30B_tokens_by-inverse_facts_and_trivia-sample_with_temperature2.0lm-1.3B-select_30B_tokens_by-facts_and_trivia-sample_with_temperature2.0lm-1.3B-select_30B_tokens_by-educational_value-sample_with_temperature2.0lm-1.3B-select_30B_tokens_by-inverse_required_expertise-sample_with_temperature1.0lm-1.3B-select_30B_tokens_by-inverse_writing_style-sample_with_temperature1.0lm-1.3B-select_30B_tokens_by-inverse_facts_and_trivia-sample_with_temperature1.0lm-1.3B-select_30B_tokens_by-educational_value-sample_with_temperature1.0lm-1.3B-select_30B_tokens_by-inverse_educational_value-sample_with_temperature1.0lm-1.3B-select_30B_tokens_by-inverse_required_expertise-sample_with_temperature2.0lm-1.3B-select_30B_tokens_by-inverse_writing_style-sample_with_temperature2.0lm-1.3B-select_30B_tokens_by-facts_and_trivia-sample_with_temperature1.0lm-1.3B-select_30B_tokens_by-inverse_educational_value-sample_with_temperature2.0lm-1.3B-select_30B_tokens_by-writing_style-sample_with_temperature2.0lm-1.3B-select_30B_tokens_by-mix_of_criteria-sample_with_temperature2.0actor_400_ppo-run-math-training-prompt-len-800-response-len-4096-bce-loss-temperature-796698f19eactor_200_ppo-run-math-training-prompt-len-800-response-len-4096-bce-loss-temperature-a568741859lm-1.3B-select_30B_tokens_by-required_expertise-sample_with_temperature2.0lm-1.3B-select_30B_tokens_by-writing_style-sample_with_temperature1.0actor_800_ppo-run-math-training-prompt-len-800-response-len-4096-bce-loss-temperature-73384f366factor_450_ppo-run-math-training-prompt-len-800-response-len-4096-bce-loss-temperature-c2ba73201bphi2-gsm8k-single-prompt-temperature-trainingzephyr-7b-gemma-adaptive_blended_loss_with_temperature_scalingoutput_iter2_ckpt_temperatureactor_600_ppo-run-math-training-prompt-len-800-response-len-4096-bce-loss-temperature-ef9e6060c9output_iter1_ckpt_temperatureoutput_iter3_ckpt_temperaturebeyond-temperature-lora-last5
