|
OpenPipe Mixture of Agents: Outperform GPT-4 at 1/25th the Cost
|
Kyle Corbitt and Saumya Gandhi |
2024-06-20 |
1,301 |
13
|
|
Introducing Direct Preference Optimization (DPO) Support on OpenPipe
|
Kyle Corbitt |
2024-10-01 |
740 |
1
|
|
Announcing Llama 3.1 and GPT-4o Mini fine-tuning through OpenPipe!
|
Kyle Corbitt |
2024-07-24 |
422 |
--
|
|
Using Reinforcement Learning and $4.80 of GPU Time to Find the Best …
|
Kyle Corbitt |
2024-10-28 |
2,044 |
217
|
|
Analyzing OpenAI’s Reinforcement Fine-Tuning: Less Data, Better Results
|
Kyle Corbitt |
2024-12-30 |
987 |
4
|
|
A Founder’s Guide to AI Fine-Tuning
|
Kyle Corbitt |
2024-10-11 |
1,028 |
--
|
|
Product Updates December 2023
|
Kyle Corbitt |
2024-01-03 |
397 |
--
|
|
What we've learned in 3 days of Llama 3
|
Kyle Corbitt |
2024-04-21 |
581 |
3
|
|
We Raised $6.7M to Replace GPT-4 with Your Own Fine-Tuned Models
|
Kyle Corbitt |
2024-03-25 |
772 |
--
|
|
Axis Improves Generation Quality and Lowers Costs With Fine Tuning
|
Kyle Corbitt |
2024-01-04 |
699 |
--
|
|
Fine-tuning Best Practices Chapter 2: Models
|
Reid Mayo |
2024-08-28 |
1,963 |
2
|
|
Fine-tuning Best Practices Series Introduction and Chapter 1: Training Data
|
Reid Mayo |
2024-08-01 |
2,048 |
3
|
|
S-LoRA: Serving Thousands of Models From One GPU for Fun and Profit
|
Kyle Corbitt |
2024-01-17 |
793 |
1
|
|
Mixtral Curious? Comparing Mistral 7B and Mixtral for fine-tuning
|
Kyle Corbitt |
2024-02-29 |
743 |
1
|
|
The Ten Commandments of Fine-Tuning in Prod (a Mastering LLMs Conference Talk)
|
Kyle Corbitt |
2024-05-23 |
603 |
--
|
|
Fine-Tuning in a Nutshell
|
- |
2024-03-28 |
1,050 |
--
|
|
One Right Answer or Many? A Useful Distinction for Evaluating and Fine-Tuning …
|
Kyle Corbitt |
2025-01-14 |
1,862 |
--
|
|
5 Deep Research Prompts that are Supercharging our Sales Strategy
|
Daniel Bolus |
2025-02-19 |
1,623 |
--
|
|
Using GRPO to Beat o1, o3-mini and R1 at "Temporal Clue"
|
Brad Hilton, Kyle Corbitt |
2025-03-06 |
2,321 |
199
|
|
pii-redact - SOTA PII Redaction on Your Laptop
|
Andie Jones |
2025-03-26 |
1,230 |
6
|
|
ART Trainer: A New RL Trainer for Agents
|
Kyle Corbitt |
2025-04-14 |
1,422 |
--
|
