Comments (1)
I think that makes sense. I have not used a seq2seq model, yet. So you might want to start with a decoder only model that should work and then compare the results to your enc-dec approach. Good luck!
from trl.
Related Issues (20)
- VLM dpo bug HOT 2
- Training on Teacher model logits HOT 3
- PPOv2Trainer throws `AttributeError: 'NoneType' object has no attribute 'modules'` because `value_model`'s default is `None` HOT 2
- `PPOv2Trainer` `reward_model` throws `AttributeError: '<My Custom Class>' object has no attribute 'base_model_prefix'`
- `PPOv2Trainer` and `RLOOTrainer`: Remove the implicit assumption that the reward model & policy model share the same tokenizer HOT 1
- `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
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.