--- language: - en license: cc-by-nc-sa-4.0 library_name: transformers pipeline_tag: any-to-any tags: - molmo - molmo-audio - multimodal - any-to-any - audio-text-to-text - image-text-to-text - audio - speech - diarization - vllm - peft - pytorch - blaster - blaster-think - cc-by-nc-sa-4.0 base_model: allenai/Molmo-7B-D-0924 base_model_relation: finetune pretty_name: "Blaster-Think" --- # Blaster-Think **Blaster-Think** is a **snapshot of the v35 hearing ship tip** (`checkpoint-116000`) plus the Loop 2 typed-think **decode contract**. Weights are the same merged serving export as live Blaster at that tip. Thinking is **not** extra LoRA in this dump: the gateway prefills `Answer: ` on cued math and strips the span before TTS. This repo is a **separate Hub model** so later GRPO / dual-LoRA work cannot overwrite the hearing ship: | Do not overwrite | This snapshot | | --- | --- | | [`molmo-audio-serving-diar-d`](https://huggingface.co/0x8badbeef/molmo-audio-serving-diar-d) | **this repo** | | [`molmo-audio-lora-diar-d`](https://huggingface.co/0x8badbeef/molmo-audio-lora-diar-d) | [`molmo-audio-lora-blaster-think`](https://huggingface.co/0x8badbeef/molmo-audio-lora-blaster-think) | `SERVE_TIP` on the live box stays `outputs/molmo-audio-lora-diar-d-v35/checkpoint-116000`. Think CE at `117500` was **aborted** (hearing dual-eval `HEARING_NO_SHIP`). Do not serve `117500`. ## What’s inside Same files as the diar-d serving merge (`model-*-of-*.safetensors`, `audio_modules.pt`, tokenizer, remote-code sources), plus: | Path | Purpose | | --- | --- | | `serving/think_scaffold.py` | Loop 2 P0/P1 cue, 192-token body, force-close, loop XOR | | `eval/think_eval_116000_gsm_192.json` | Scaffolded GSM heldout at this tip | | `SNAPSHOT.json` | Pin: tip id, parent, abort notes | ## Think eval (this tip, scaffolded GSM, n=20) | Gate | Result | | --- | --- | | Format (``…``) | **20/20** | | Exact | **8/20** (worded finals and a few real misses; not a ship gate for think) | | Unearned correct | 0 | | Uncued leak | 0 | Exact is a **format contract + weak arithmetic**, not a reason to invert training from base Molmo-7B-D. ## Intended use - Restore this exact 116000 merge if GRPO or a second think LoRA goes wrong - Research on cued typed thinking **without** replacing live Blaster ## License **[CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/)**. Private unless the owner changes visibility. Marketing name: **Blaster-Think**. Technical Hub id: `molmo-audio-serving-blaster-think`.