Summary:
Create a script for simple generation from BLT
Test Plan:
```
python -m bytelatent.generate_blt config=../internal-blt/configs/eval_blt.yaml
```
- PPL/validation: Works now and uses multi-gpu. For some reason 1 GPU differs from multi-GPU, can debug in a followup PR
- Generation evals likely work, but are very slow, so disabled for now
Test Plan:
```
torchrun --nproc-per-node 8 -m bytelatent.eval config=../internal-blt/configs/eval.yaml
```
Summary:
- Refactor local model configs to be separate and clearer
- Add attention arguments and correct which attention is used in local models
- Preparation for being able to have an entropy train script
- Fix failing unit tests
Test Plan:
