Downloads · 30 days
0
Flow-Aligned-Distillation
NYCU-MLLab/Flow-Aligned-Distillation
Flow-Aligned-Distillation is a text generation model from NYCU-MLLab. Use it when you need the model to write or continue text. It is set up for pytorch. The card lists the license as other.
This private artifact repository contains the six seed-44 FAD best-validation training checkpoints used for the 3B/8B, 15%/20%/25% operating points.
Access
Public
Updated Aug 21, 2026
Repo size
33 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt33 GB · 100%
At a glance
- Task
- Text Generation
- Library
- pytorch
- License
- other
- Access
- Public
- Created
- Aug 21, 2026
- Updated
- Aug 21, 2026
- SHA
- c5fbeed2
Try a prompt
Base models
Model card
From the Hugging Face model README
Flow-Aligned Distillation checkpoints
This private artifact repository contains the six seed-44 FAD best-validation training checkpoints used for the 3B/8B, 15%/20%/25% operating points.
These files are custom PyTorch training checkpoints, not standalone
Transformers from_pretrained directories. Load them with the FAD pipeline in
the companion code repository:
https://github.com/hanklin9188/Flow-Aligned-Distillation
Checkpoints
| Backbone | Nominal budget | Stored FFN banks | Seed | Best validation step | File |
|---|---|---|---|---|---|
| Llama-3.2-3B | 15% | 22 | 44 | 4,500 | checkpoints/llama-3.2-3b/fad-15pct-k22-seed44.pt |
| Llama-3.2-3B | 20% | 19 | 44 | 4,500 | checkpoints/llama-3.2-3b/fad-20pct-k19-seed44.pt |
| Llama-3.2-3B | 25% | 17 | 44 | 4,500 | checkpoints/llama-3.2-3b/fad-25pct-k17-seed44.pt |
| Llama-3.1-8B | 15% | 25 | 44 | 7,500 | checkpoints/llama-3.1-8b/fad-15pct-k25-seed44.pt |
| Llama-3.1-8B | 20% | 23 | 44 | 9,500 | checkpoints/llama-3.1-8b/fad-20pct-k23-seed44.pt |
| Llama-3.1-8B | 25% | 20 | 44 | not recorded | checkpoints/llama-3.1-8b/fad-25pct-k20-seed44.pt |
The 8B 25% run retains its best-validation training checkpoint but does not
have a completed shared_student.pt or deploy_bundle.pt export in the source
archive. It is published here as a recoverable training checkpoint and should
be exported with the companion pipeline before deployment.
Training contract
- objective: decision-token CE + FAD functional alignment
- private adapter: rank/alpha 128/128
- seed: 44
- checkpoint selection: minimum validation
decision_ce - 3B projection rank: 256
- 8B projection rank: 512
External requirements
The checkpoints do not redistribute Meta Llama base weights, merged teacher weights, tokenizer files, datasets, or licenses. Users must obtain the matching base model and teacher artifacts separately and comply with Meta's model terms.
SHA256SUMS is generated before upload and is the integrity authority for the
six checkpoint files.
- Task
- Text Generation
- Library
- pytorch
- License
- other
- Created
- Aug 21, 2026
- Updated
- Aug 21, 2026