Duplicate from maxbittker/opus-k26-dsl-step150-2026-05-02

Co-authored-by: max bittker <maxbittker@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,60 @@
+---
+license: other
+base_model: moonshotai/Kimi-K2.6
+library_name: tinker
+tags:
+  - lora
+  - rl
+  - opus-magnum
+  - dsl
+---
+
+# opus-k26-dsl-step150-2026-05-02
+
+LoRA adapter trained with reinforcement learning (GRPO via Thinking Machines'
+Tinker SDK) on the Opus-Magnum puzzle-solving REPL benchmark, snapshotted at
+training step **150**.
+
+## Training setup
+
+- **Base model:** `moonshotai/Kimi-K2.6`
+- **Renderer:** `kimi_k25`
+- **Representation:** `dsl` (action language the agent emits)
+- **Adapter:** LoRA, rank `32`
+- **RL recipe:** GRPO via Tinker
+- **Hyperparameters:**
+  - `learning_rate = 1e-5`
+  - `group_size = 8`, `groups_per_batch = 16`
+  - `max_tokens = 1024`, `max_trajectory_tokens = 12000`
+  - `distances = 1,2,3,4`
+  - `max_steps_off_policy = None`
+  - `save_every = 5`
+
+## Files
+
+- `adapter_model.safetensors` — Tinker raw LoRA adapter weights
+- `adapter_config.json` — adapter metadata (rank, alpha, target modules)
+- `README.md` — this file
+
+## Provenance
+
+Tinker checkpoint:
+```
+tinker://94a8b593-adf6-5f99-a986-4dd98d183887:train:0/sampler_weights/000150
+```
+
+## Converting to PEFT format
+
+The files above are in Tinker's raw adapter format. To convert to PEFT format
+suitable for direct vLLM `--lora-modules` loading, run on a machine that can
+host the base model:
+
+```python
+from tinker_cookbook.weights import build_lora_adapter
+
+build_lora_adapter(
+    base_model="moonshotai/Kimi-K2.6",
+    adapter_path="./tinker_adapter",   # this repo's contents
+    output_path="./peft_adapter",
+)
+```

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": false,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "all-linear",
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8d0d3437ac42f00f26a210f8490792bd8017a4ad0436225d121cc1969a653cf
+size 18777115704