SemanticScuttle - klotz.me

klotz: dpo*

Bookmarks on this page are managed by an admin user.

0 bookmark(s) - Sort by: Date ↓ / Title / - Bookmarks from other users for this tag

1. NousResearch Released Nous-Hermes-2-Mixtral-8x7B: An Open-Source LLM with SFT and DPO Versions

   Trained on a vast dataset comprising primarily GPT-4 generated data and supplemented with high-quality information from open datasets in the AI field, this model exhibits exceptional performance across various tasks. It introduces a novel SFT + DPO version, and for those who prefer a different approach, an SFT-only version is also made available

   2024-01-26 Tags: llm, nous, dpo, sft by klotz
2. Preference Tuning LLMs with Direct Preference Optimization Methods

   2024-01-18 Tags: llm, dpo, fine tuning, huggingface by klotz
3. Fine-tune a Mistral-7b model with Direct Preference Optimization

   Boost the performance of your supervised fine-tuned models

   2024-01-02 Tags: llm, dpo, mistral by klotz

Top of the page

First / Previous / Next / Last / Page 1 of 0