corpus.blog
41,554 blogs · 5,181,941 posts Claim your blog
Record · corpus.blog/posts/01a087c2-4503-712d-b220-aa8f04c9d6e4

How to align open LLMs in 2025 with DPO and and synthetic data

philschmid.de · published 23 January 2025

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 philschmid.de Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
External links
19
Words captured
3,031

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://huggingface.co/papers/2305.18290
huggingface.co
https://huggingface.co/papers/2203.02155
huggingface.co
https://huggingface.co/papers/2310.11523
huggingface.co
https://huggingface.co/nicolinho/QRM-Llama3.1-8B-v2
huggingface.co
https://huggingface.co/models
huggingface.co
https://huggingface.co/join
huggingface.co
https://arxiv.org/abs/2404.14367
arxiv.org
https://arxiv.org/abs/2403.10160
arxiv.org
https://huggingface.co/datasets/philschmid/DMath
huggingface.co
https://aclanthology.org/2023.emnlp-main.927.pdf
aclanthology.org
https://github.com/philschmid/deep-learning-pytorch-huggingface/blob/main/training/scripts/dpo/create_preference_dataset.py
github.com
https://huggingface.co/philschmid/philschmid-llama-3-1-8b-math-orca-spectr-philschmid-DMath-candidates
huggingface.co
https://huggingface.co/docs/trl/dpo_trainer
huggingface.co
https://github.com/philschmid/deep-learning-pytorch-huggingface/blob/main/training/scripts/dpo/run_dpo.py
github.com
https://github.com/huggingface/alignment-handbook
github.com
https://github.com/philschmid/deep-learning-pytorch-huggingface/blob/main/training/receipes/dpo-llama-3-1-8b-qlora.yaml
github.com
https://huggingface.co/datasets/openai/gsm8k
huggingface.co
https://github.com/EleutherAI/lm-evaluation-harness
github.com
https://github.com/huggingface/text-generation-inference
github.com
Elsewhere on philschmid.de (5)