-
### 1. What is your project? (max 100 words)
(Our project is called FlowModel during Chainlink Spring 2022 Hackathon, which is renamed as BlockModel now.)
BlockModel is a R&D infrastructure …
-
```
torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 2.00 MiB (GPU 0; 22.20 GiB total capacity; 20.67 GiB already allocated; 4.12 MiB free; 21.14 GiB reserved in total by PyTorch) I…
-
### 🐛 Describe the bug
相关日志：
WARNING:torch.distributed.run:
*****************************************
Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid you…
-
Brian Mckenna criticised current spec. He proposes to use FP approach to achieve much better modularity.
Suggest to read it, really good ideas with just three changes.
http://brianmckenna.org/blog/c…
-
Towards replication of ELM Stage 3, I'm looking into adding softprompts to train a conditional learnable embedding with PPO for each terrain mentioned in the paper.
Following https://github.com/kip…
-
### 🐛 Describe the bug
When I ran `accelerate launch examples/ppo_sentiments.py`, the error below happened. Am I supposed to unwrap the ddp model?
```
AttributeError: 'DistributedDataParallel' obje…
-
@jmhessel @dirkgr @schmmd @iellenberger
Ran python scripts/training/train_text_generation.py --config_path scripts/training/task_configs/iwslt2017/t5_ppo.yml
with the following config:
`…
-
In `docs/algorithms`, we need to add entries for:
- [x] MCE IRL
- [x] Preference Comparison
- [x] Density Baseline
We should also add an introduction/basic guidance to the existing algor…
-
# Related Reference
- O'Keefe J, Dostrovsky J. [The hippocampus as a spatial map: Preliminary evidence from unit activity in the freely-moving rat](https://psycnet.apa.org/record/1972-08318-001).
…
-
### Proposal
Include the Hutter Prize corpus ([enwik9](http://mattmahoney.net/dc/enwik9.zip)) as a "game" for the purpose of sample-efficient reinforcement language modeling.
### Motivation
…