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.
tiny-random-Llama-3-valueheadLlama-3-8b-gsm8k-value-Agpt2-xl-ft-value_it-1k-0_on_1k-1ValueLlama-3-8BLlama-3-8b-gsm8k-value-B1.5B-value-iteration_2bloom-7b1-ccp2-r16-query_key_valueLlama-2-7b-hf-valueeval-22-1-epochs-level2lm-1.3B-select_30B_tokens_by-educational_value-sample_with_temperature2.0lm-1.3B-select_30B_tokens_by-educational_value-top_klm-1.3B-select_30B_tokens_by-inverse_educational_value-sample_with_temperature1.0Llama-2-7b-hf-valueeval-1-epochs-level1lm-1.3B-select_30B_tokens_by-inverse_educational_value-top_kValue_func_raw_prefix_Qwen3-4B-InstructLlama-2-7b-hf-human-values-booleanLlama-2-7b-hf-valueeval-22-1-epochs-level1falcon-7b-Open-Platypus_2.5w-r16-query_key_valuelm-1.3B-select_30B_tokens_by-educational_value-sample_with_temperature1.0lm-1.3B-select_30B_tokens_by-inverse_educational_value-sample_with_temperature2.00.5B-value-iteration_6Llama-2-7b-hf-valueeval-3-epochsfalcon-7b-ccp2-r16-query_key_value0.5B-value-iteration_0valueClassify-v00.5B-value-iteration_11.5B-value-iteration_31.5B-value-iteration_4phi-finetuned-values2Qwen2.5-Math-1.5B-OREO-Value_MATH_training_Qwen2.5-32B-Instructgpt2_constitutional_classifier_with_value_head