notux-8x7b-v1-AWQ
Chat & support: TheBloke’s Discord server Want to contribute? TheBloke’s Patreon page TheBloke’s LLM work is generously supported...
Метка: DPO
xDAN-L1-Chat-RL-v1-GPTQ
Chat & support: TheBloke’s Discord server Want to contribute? TheBloke’s Patreon page TheBloke’s LLM work is generously supported...
SauerkrautLM-Mixtral-8x7B-AWQ
Chat & support: TheBloke’s Discord server Want to contribute? TheBloke’s Patreon page TheBloke’s LLM work is generously supported...
SauerkrautLM-Mixtral-8x7B-Instruct-GPTQ
Chat & support: TheBloke’s Discord server Want to contribute? TheBloke’s Patreon page TheBloke’s LLM work is generously supported...
notus-7B-v1-AWQ
Chat & support: TheBloke’s Discord server Want to contribute? TheBloke’s Patreon page TheBloke’s LLM work is generously supported...
archangel_sft-kto_llama13b
This repo contains the model checkpoints for: — model family llama13b — optimized with the loss SFT+KTO —...
NeuralHermes-2.5-Mistral-7B-5.0bpw-h6-exl2
NeuralHermes представляет собой модель teknium/OpenHermes-2.5-Mistral-7B, которая была дополнительно доработана с помощью оптимизации прямых предпочтений (DPO) с использованием набора...
notus-7b-v1-lora-adapter
Notus is a collection of fine-tuned models using Direct Preference Optimization (DPO) and related RLHF techniques. This model...
zephyr-7b-dpo-full
This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on...
academic-humanize-qwen25-7b-dpo-v2-lora
This repository contains the DPO-v2 LoRA adapter for Academic Humanize, a post-training project for reducing AI-like patterns in...