Comments (2)
Hi, thanks for the great work. I also want to know whether and how it can be used for masked token predictions. Thanks in advance!
from trl.
Reinforcement learning is designed for sequential decision problems and thus works well for causal language modeling (such as GPT-2). BERT however does not fall in that category since it is a one-shot prediction and not a sequential prediction such as in language modeling. So I don't think it is straight forward to adapt this approach.
from trl.
Related Issues (20)
- `PPOTrainer` OOM Error Because of Forced Upcast to `torch.float32` HOT 1
- how to convert dpodata to ktodata HOT 1
- [Question] Why TR-DPO default alpha and tau don't match the values suggested in the paper?
- Why is num_labels=1 in the reward_madeling.py script? HOT 1
- Correct masking when the same roles are present in adjacent messages in DataCollatorForCompletionOnlyLM
- CUDA error: device-side assert triggered HOT 3
- Does PPOV2 not support PEFT or Lora?
- Can DPO be used to shorten the model response length preference? HOT 2
- Fine-tune large vision language model for chat completion only HOT 2
- Question: Does `trl` support training on AMD GPUs? HOT 2
- `OnPolicyConfig`: Change `non_eos_penalty` to be more clearly documented and consistent across different trainers HOT 5
- Can model be `None`? HOT 1
- Example Scripts/Commands for Creating SFT & Reward Models for PPO/RLOO/Other Trainers HOT 2
- Different with online dpo papers HOT 1
- finetuning gemma2-2b with multi-gpu get OOM, how do i only do model sharding and no data parallel(i guess it's going into DDP). HOT 2
- I'm closing this issue because no one has provided any code to reproduce the error. If you think you are facing the same problem, please open another issue (link this one) with a precise description and a code to reproduce the error.
- Negative Entropy in TRL PPOv2Trainer TLDR Example HOT 3
- Clarification of 2 Entropies in PPOv2Trainer Documentation
- `OnPolicyConfig` - Rename or revise `num_sample_generations` HOT 1
- AttributeError: 'PPOv2Trainer' object has no attribute 'deepspeed' HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from trl.