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.
LLM2Vec-Meta-Llama-3-8B-Instruct-mntpSkywork-Reward-Llama-3.1-8B-v0.2URM-LLaMa-3.1-8BLLM2Vec-Meta-Llama-3-8B-Instruct-mntp-supervisedtiny-LlamaForSequenceClassification-3.2ArmoRM-Llama3-8B-v0.1Skywork-Reward-V2-Llama-3.1-8BSkywork-Reward-V2-Llama-3.2-1BSkywork-Reward-V2-Llama-3.1-8B-40MSkywork-Reward-V2-Llama-3.2-3Bllama-3-tulu-2-8b-uf-mean-rmGRM-Llama3.2-3B-rewardmodel-ftFsfairX-LLaMA3-RM-v0.1Llama-3.1-8B-Instruct-RM-RB2Skywork-Reward-Llama-3.1-8Bllama-7b-rm-float32LLM2Vec-Meta-Llama-3-8B-Instruct-mntpllama-3.1-8b-oracle-rm-hh-rlhf-harmlessnessllama-3.1-8b-oracle-rm-hh-rlhf-helpfulnessLLM2Vec-Meta-Llama-3-8B-Instruct-mntp-supervisedllama-3.1-nemoguard-8b-content-safetyLlama-3.1-Tulu-3-8B-RMllama-3.1-nemoguard-8b-topic-controlLlama-3-OffsetBias-RM-8BGRM_Llama3.1_8B_rewardmodel-fthh_rlhf_rm_open_llama_3bLLM2Vec-Meta-Llama-31-8B-Instruct-mntpLLM2Vec-Meta-Llama-31-8B-Instruct-mntp-unsup-simcseLlama-Guard-3-1B-GGUFLLM2Vec-Meta-Llama-3-8B-Instruct-mntp-unsup-simcse