We’re open-sourcing our text-to-image model and the process behind it
•
68
Blog, Articles, and discussions
Community Articles
view all
vllmgrpotrl
No GPU left behind: Unlocking Efficiency with Co-located vLLM in TRL
- +2
95
June 3, 2025
vlmmultimodaltrl
Preference Optimization for Vision Language Models
87
July 10, 2024
researchrlrlhf
Putting RL back in RLHF
107
June 12, 2024
researchrlrlhf
Constitutional AI with Open LLMs
- +3
17
February 1, 2024
rlrlhfnlp
Preference Tuning LLMs with Direct Preference Optimization Methods
-
-
-
- +1
74
January 18, 2024
researchrlrlhf
The N Implementation Details of RLHF with PPO
71
October 24, 2023
guidediffusersrl
Finetune Stable Diffusion Models with DDPO via TRL
19
September 29, 2023
rlrlhfnlp
Fine-tune Llama 2 with DPO
65
August 8, 2023
rlrlhfnlp
StackLLaMA: A hands-on guide to train LLaMA with RLHF
-
-
-
- +3
46
April 5, 2023
rlrlhfnlp
Fine-tuning 20B LLMs with RLHF on a 24GB consumer GPU
-
-
-
- +2
68
March 9, 2023
llmsrlhfred-teaming
Red-Teaming Large Language Models
34
February 24, 2023
rlhfChatGPTcot
What Makes a Dialog Agent Useful?
2
January 24, 2023
rlhfrlguide
Illustrating Reinforcement Learning from Human Feedback (RLHF)
373
December 9, 2022
We’re open-sourcing our text-to-image model and the process behind it
•
68
Apriel-H1: The Surprising Key to Distilling Efficient Reasoning Models
•
20
Text-to-image Architectural Experiments
•
33
Introducing Cogito v2.1
•
17
Projected Abliteration
•
28
AI Model Optimization More Flexible Than Ever
•
12
The Heterogeneous Feature of RoPE-based Attention in Long-Context LLMs
•
11
How to make NeuTTS-air generate over 200 seconds of audio in a single second.
•
10
ViDoRe V3: a comprehensive evaluation of retrieval for enterprise use-cases
•
50
Norm-Preserving Biprojected Abliteration
•
15
The Pharmome Map: a comprehensive public dataset for drug-target interaction modeling
•
9
KV Caching Explained: Optimizing Transformer Inference Efficiency
•
177
To Think or Not to Think: A Router for Hybrid LLMs
•
8
Uncensor any LLM with abliteration
•
722
🧠 SQaLe: Enabling new Text-to-SQL models with our massive dataset
•
6
Why Did MiniMax M2 End Up as a Full Attention Model?
•
65
The 1 Billion Token Challenge: Finding the Perfect Pre-training Mix
•
41
Code a simple RAG from scratch
•
248
Visualizing How VLMs Work
•
45
Granite 4.0 Nano: Just how small can you go?
•
119