Qwen35-0.8B-FlyEmbedding-v31
Research artifact from TinyCeNN-LM. Architecture: Qwen3.5-0.8B + FlyEmbedding-v3.1 preservation-first residual adapter.
Architecture
- Architecture/run type:
Qwen3.5-0.8B + FlyEmbedding-v3.1 preservation-first residual adapter - Base model:
Qwen/Qwen3.5-0.8B - Dataset:
Not recorded - Source code: https://github.com/vtavakkoli/TinyCeNN-LM
Latest saved results
| Metric | Value |
|---|---|
stop_reason | preservation boundary crossed at step 100: top1=0.984375, kl=0.000834 |
The Hugging Face repository keeps timestamped run artifacts under runs/. This preserves training reports, configs and run metadata independently of the temporary Colab filesystem.
Saved experiment files
config.jsonflyembedding_report.jsongeneration_config.jsonlm_eval_fly_results.jsonlm_eval_qwen_results.jsontokenizer_config.json
Reproducibility
Run the matching notebook from the TinyCeNN-LM repository. Colab notebooks use a Hugging Face write token from the HF_TOKEN Colab Secret; tokens should never be pasted into notebook source.
Limitations
This is a research checkpoint. Metrics saved here are the metrics produced by the corresponding training notebook/script; unless explicitly marked as held-out evaluation, they should not be treated as publication-grade benchmark results. Generation quality can differ substantially from the base model.
Citation
If you use this experimental checkpoint, cite the TinyCeNN-LM repository and the upstream base model.