G1b adapter and model card

README.md

@@ -0,0 +1,67 @@
+---
+license: apache-2.0
+base_model: meta-models/Muse-Glimmer-30B
+library_name: peft
+tags: [robotics, program-synthesis, lora, qlora, manipulation]
+---
+
+# show-once · Glimmer program writer (G1b)
+
+A QLoRA adapter for [Muse Glimmer 30B](https://huggingface.co/meta-models/Muse-Glimmer-30B). Given a task intent
+(explicit rules such as "every cube into the red box") and the robot's object list, it writes a short, checkable
+Python program against the robot API of [show-once](https://github.com/allwinlucious/show-once): `find`,
+`find_all`, `pick`, `place`, `verify`, and so on. The program is checked, dry-run and executed by the robot stack.
+The model never issues motions itself.
+
+## Training
+
+*   **Data:** 711 expert rows from the planning simulator ("plan tier": the real motion planner and robot
+    service, no physics):
+    *   for every training task, every pick-order strategy was run;
+    *   the label is the most reliable strategy that succeeded;
+    *   5 task families (cluster, packing, stacking, reach, sorting), 562 rows plus 149 sorting rows.
+*   **Method:** supervised fine-tuning with the model cookbook's QLoRA recipe:
+    *   r 32, alpha 16, dropout 0.05;
+    *   attention and MLP projections of the language model;
+    *   NF4 base.
+
+## Results
+
+Held-out tasks: 250 tasks (50 per family, including the never-trained `mixed` family), 3 runs per program. 95%
+intervals are a bootstrap over tasks.
+
+| | success |
+|---|---|
+| Glimmer, no adapter | 61% [56–67] |
+| **this adapter** | **86% [82–89]** |
+| best fixed strategy per family (reference) | 84% |
+| oracle (any strategy) | 91% |
+
+*   **Stacking:** 47% → 97%.
+*   **The unseen family:** 51% → 82%.
+*   **Isaac Sim physics** (50 held-out tasks): 41/50, against 34/50 without the adapter.
+
+What it learned is which strategy works for which kind of task. It did not learn per-scene judgement: the oracle
+is not reached.
+
+Full results, ablations (rejection sampling, DPO, GRPO, bf16 LoRA, seeds) and limitations:
+`docs/designs/learning_results.md` in the repository.
+
+## Use
+
+Load it on the NF4 base, as the cookbook evaluates adapters: transformers + PEFT. The repository's
+`learn/chat_server.py` serves the base model and this adapter behind an OpenAI-compatible API:
+
+```
+python learn/chat_server.py --root <dir containing runs/G1b> --adapters G1b
+```
+
+## Limitations
+
+*   Synthetic tabletop tasks only (cubes, boxes, plates).
+*   Strategy-level decisions only: grasps and motion stay with the robot stack.
+*   Physics results are on 50 tasks.
+
+## License
+
+Apache-2.0, as the base model. This adapter is a derivative of Muse Glimmer 30B, fine-tuned as described above.

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-models/Muse-Glimmer-30B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "model\\.language_model\\.layers\\.\\d+\\.(self_attn\\.(q|k|v|o)_proj|mlp\\.(gate|up|down)_proj)",
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36f6e344d7e3432f96d34e0929e04d0b7633ccb84f594b799bd561aae9341182
+size 766880464