vtava/Qwen35-0.8B-FlyFFN-v3-AllFFN

Qwen35-0.8B-FlyFFN-v3-AllFFN

Research artifact from TinyCeNN-LM. Architecture: Qwen3.5-0.8B + FlyFFN-v3 on all 24 FFNs (no dense anchors).

Architecture

• —Architecture/run type: Qwen3.5-0.8B + FlyFFN-v3 on all 24 FFNs (no dense anchors)
• —Base model: Qwen/Qwen3.5-0.8B
• —Dataset: Not recorded
• —Source code: https://github.com/vtavakkoli/TinyCeNN-LM

Latest saved results

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

• —.hf_run_archive/standalone-20260919T081146Z/config.json
• —.hf_run_archive/standalone-20260919T081146Z/flyffn_config.json
• —.hf_run_archive/standalone-20260919T081146Z/generation_config.json
• —.hf_run_archive/standalone-20260919T081146Z/report.json
• —.hf_run_archive/standalone-20260919T081146Z/tokenizer_config.json
• —config.json
• —flyffn_config.json
• —generation_config.json
• —report.json
• —tokenizer_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.