corpus.blog
41554 blogs · 4,504,310 posts Claim your blog
Record · corpus.blog/posts/01a08c59-e015-713c-8022-8858223d86e8

Direct Preference Optimization Explained In-depth

tylerromero.com · published 13 April 2024

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at tylerromero.com Wayback capture
2blogs citing
First cited
25 Oct 2025
Most recent
8 May 2026
Rank this month
not ranked
Links from this post
37
Words captured
3,712

Cited by

Blog
In the post
Date
magnusross.github.io
An idiot's guide to lead optimisation for proteins Read at the source ↗
8 May 2026
desh2608.github.io
Notes from the RLHF book Read at the source ↗
25 Oct 2025

Links from this post

Link
Host
https://arxiv.org/abs/2305.18290
arxiv.org
https://arxiv.org/abs/2005.14165
arxiv.org
https://ai.meta.com/blog/meta-llama-3/
ai.meta.com
Mistral 7B
mistral.ai
https://crfm.stanford.edu/2023/03/13/alpaca.html
crfm.stanford.edu
https://lmsys.org/blog/2023-03-30-vicuna/
lmsys.org
https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
huggingface.co
https://ai.meta.com/blog/meta-llama-3
ai.meta.com
https://cdn.openai.com/papers/gpt-4-system-card.pdf
cdn.openai.com
https://www.anthropic.com/news/claude-3-family
anthropic.com
https://blog.google/technology/ai/google-gemini-ai
blog.google
https://arxiv.org/abs/2312.11805
arxiv.org
How to generate text: using different decoding methods for language generation with Transformers Read at the source ↗
huggingface.co
https://lukesalamone.github.io/posts/what-is-temperature/
lukesalamone.github.io
https://chat.lmsys.org/
chat.lmsys.org
https://huggingface.co/datasets/lmsys/chatbot_arena_conversations
huggingface.co
https://huggingface.co/datasets/openai/webgpt_comparisons?row=1
huggingface.co
https://huggingface.co/datasets/Anthropic/hh-rlhf
huggingface.co
https://www.chess.com/terms/elo-rating-chess
chess.com
https://liquipedia.net/starcraft/Elo_rating
liquipedia.net
https://www.goratings.org/en/
goratings.org
https://lmsys.org/blog/2023-12-07-leaderboard/
lmsys.org
https://pytorch.org/docs/stable/generated/torch.nn.NLLLoss.html
pytorch.org
https://platform.openai.com/tokenizer
platform.openai.com
https://github.com/karpathy/minbpe
github.com
https://cookbook.openai.com/examples/using_logprobs
cookbook.openai.com
https://en.wikipedia.org/wiki/Kullback%E2%80%93Leibler_divergence
en.wikipedia.org
https://arxiv.org/pdf/2006.05990.pdf
arxiv.org
https://en.wikipedia.org/wiki/Gibbs%27_inequality
en.wikipedia.org
https://arxiv.org/abs/2310.12036
arxiv.org
https://openai.com/research/instruction-following
openai.com
https://arxiv.org/abs/2203.02155
arxiv.org
Fine-tune Llama 2 with DPO Read at the source ↗
huggingface.co
https://arxiv.org/abs/2404.03715
arxiv.org
http://wittawat.com/posts/log-sum_exp_underflow.html
wittawat.com
https://arxiv.org/abs/2006.05990
arxiv.org
https://arxiv.org/abs/2206.12301
arxiv.org