corpus.blog
Most cited
Talked about
Blogs
57,803 blogs · [ { "id": "01a08759-1b42-71b2-997c-da4037b695cf", "title": "Training Tiny LLMs to Play Connections Better than Frontier Models", "url": "https://brianfitzgerald.xyz/connections", "published_at": "2025-05-22T00:00:00+00:00" }, { "id": "01a08759-1b42-71b2-997c-da40385fd68a", "title": "Training a Reasoning Model for Very Cheap with DPO", "url": "https://brianfitzgerald.xyz/dpo-for-step-wise-reasoniong", "published_at": "2025-01-07T00:00:00+00:00" }, { "id": "01a08759-1b42-71b2-997c-da4038e9793f", "title": "Reviewing Post-Training Techniques from Recent Open LLMs", "url": "https://brianfitzgerald.xyz/dpo-review", "published_at": "2024-12-13T00:00:00+00:00" }, { "id": "01a08759-1b42-71b2-997c-da4038f0b449", "title": "Curriculum Learning with DPO and Logit Pruning", "url": "https://brianfitzgerald.xyz/dpo-pruning", "published_at": "2024-11-28T00:00:00+00:00" }, { "id": "01a08759-1b42-71b2-997c-da4039cabf9d", "title": "Tiny Agents - Training Small LLMs to Use Tools with DPO and Synthetic Data", "url": "https://brianfitzgerald.xyz/tool-use-dpo", "published_at": "2024-03-11T00:00:00+00:00" }, { "id": "01a08759-1b42-71b2-997c-da403a7cf218", "title": "SuperPrompt - Better SDXL prompts in 77M Parameters", "url": "https://brianfitzgerald.xyz/prompt-augmentation", "published_at": "2024-02-24T00:00:00+00:00" }, { "id": "01a08759-1b42-71b2-997c-da403ac320ab", "title": "Understanding StyleAligned", "url": "https://brianfitzgerald.xyz/style-aligned", "published_at": "2024-01-28T00:00:00+00:00" }, { "id": "01a08759-1b42-71b2-997c-da403b03fc7c", "title": "Longer videos with Stable Video Diffusion via YaRN", "url": "https://brianfitzgerald.xyz/svd-extension", "published_at": "2023-12-20T00:00:00+00:00" } ] posts
Claim your blog
Back to brianfitzgerald.xyz
Blog · corpus.blog/blogs/brianfitzgerald.xyz/posts
brianfitzgerald.xyz
brianfitzgerald.xyz
2025
Training Tiny LLMs to Play Connections Better than Frontier Models
original ↗
22 May 2025
Training a Reasoning Model for Very Cheap with DPO
original ↗
7 Jan 2025
2024
Reviewing Post-Training Techniques from Recent Open LLMs
original ↗
13 Dec 2024
Curriculum Learning with DPO and Logit Pruning
original ↗
28 Nov 2024
Tiny Agents - Training Small LLMs to Use Tools with DPO and Synthetic Data
original ↗
11 Mar 2024
SuperPrompt - Better SDXL prompts in 77M Parameters
original ↗
24 Feb 2024
Understanding StyleAligned
original ↗
28 Jan 2024
2023
Longer videos with Stable Video Diffusion via YaRN
original ↗
20 Dec 2023