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.
LLaMA3.1-8B-Instruct-DFlash-UltraChatllama3.18binstruct-prm-lora-correctness-10epochsllama3.18binstruct-prm-lora-step-continuation-2epochsllama3.18binstruct-gsm8k-lora-step-continuation-5epochsLLaMA3.1-8B-Instruct-DFlash-UltraChatllama3.18binstruct-prm-lora-correctness-5epochsllama3.18binstruct-prm-lora-step-continuation-10epochsLlama-3.1-8B-bnb-4bitllama3.18binstruct-prm-lora-correctness-2epochsllama3.18binstruct-gsm8k-lora-correctness-5epochsLlama3.1-8b-Quant-4bitsllama3.18binstruct-prm-lora-step-continuation-5epochsLlama-3.1-8B-Instruct-NLRL-TicTacToe-PolicyLlama-3.1-8B-Instruct-NLRL-TicTacToe-ValueLlama-3.1-8B-Instruct-NLRL-Breakthrough-ValueLlama-3.1-8B-Instruct_p_en_q_rullama3.18binstruct-stqa-lora-step-continuation-5epochsllama3.18binstruct-stqa-lora-step-continuation-2epochsllama3.18binstruct-sciqa-lora-correctness-2epochsLlama-3.1-8B-Instruct_p_en-ur-ru_q_ruLlama-3.1-8B-Instruct_p_en_q_ru-urLlama-3.1-8B-Instruct_p_en-ru_q_rullama-3.1-8b_full_50pct_3neighbors-10eps-bs32-lr2e_1-2epsLlama-3.1-8B-medquad-V3-weight-pruning015LLaMA3.1-8B-Instruct-DFlash-UltraChat-GGUF