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-valueheadValue4AI-ValueLlama-3-8B-GGUFLlama-3-8b-gsm8k-value-Agpt2-xl-ft-value_it-1k-0_on_1k-1Llama-3-8b-gsm8k-value-BValueLlama-3-8B1.5B-value-iteration_2bloom-7b1-ccp2-r16-query_key_valueValue_func_raw_prefix_Qwen3-4B-Instructlm-1.3B-select_30B_tokens_by-educational_value-sample_with_temperature2.0lm-1.3B-select_30B_tokens_by-educational_value-top_kLlama-2-7b-hf-valueeval-22-1-epochs-level2lm-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_kLlama-2-7b-hf-human-values-booleanfalcon-7b-Open-Platypus_2.5w-r16-query_key_valuefalcon-7b-ccp2-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_temperature2.0Llama-2-7b-hf-valueeval-22-1-epochs-level10.5B-value-iteration_6Llama-2-7b-hf-valueeval-3-epochs0.5B-value-iteration_0Qwen2.5-Math-1.5B-OREO-Value_MATH_training_Qwen2.5-32B-Instruct0.5B-value-iteration_11.5B-value-iteration_31.5B-value-iteration_4gpt2_constitutional_classifier_with_value_headphi-finetuned-values2