TB2 SFT LoRA train adapter (raw PEFT, step 250)

README.md

@@ -0,0 +1 @@
+Raw Tinker PEFT adapter for GRPO training (HF key format). For vLLM serve use `lilyzhng/gpt-oss-20b-tb2-sft-lora`.

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "peft_type": "LORA",
+  "auto_mapping": null,
+  "base_model_name_or_path": "openai/gpt-oss-20b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 32,
+  "lora_dropout": 0.0,
+  "modules_to_save": null,
+  "r": 32,
+  "rank_pattern": {},
+  "alpha_pattern": {},
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "lm_head",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31f1fede2d9a099991c44f02bef0c1befab83ca8b282ef145c1c0039603c3f0e
+size 1789194032