Stage 6 LoRA r=4: oracle-preserved, weak-negative on Probe-G

.gitattributes

@@ -0,0 +1,2 @@
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,42 @@
+---
+license: cc-by-nc-4.0
+tags:
+  - lora
+  - peft
+  - speech-language-models
+  - frozen-adapter
+base_model: Qwen/Qwen3-8B
+---
+
+# BTA — Stage 6 LoRA r=4
+
+Minimal-LoRA upper-bound experiment: rank 4, α=16 (α/r=4) on
+Qwen3-8B `q_proj`/`v_proj` across all 36 transformer blocks (72 LoRA
+modules total, ~1.92M LoRA parameters). The R1.8 adapter and
+$C_\phi$ heads are FROZEN; only the LoRA matrices update.
+
+**Pre-registered oracle-stability gate:** Probe-G-oracle re-confirm
+within ±2pp of the Stage 1a anchor 0.7871. Result: 0.7970 (+0.99pp drift) → PASS.
+
+**Outcome branch:** weak-negative. Probe-G$_{\mathrm{neutral}}$ = 0.4926
+(R0 - 0.0196), 0.4pp below the H2 NULL band on the negative side.
+Minimal LoRA at this rank preserves the oracle but does not recover
+audio-conditional consumer use of the R1.8 representation.
+
+**Files:** PEFT LoRA weights (`adapter_config.json`, `adapter_model.safetensors`).
+Load via `PeftModel.from_pretrained` on top of base `Qwen/Qwen3-8B`.
+
+**Files / metrics:**
+
+| | Value |
+|---|---|
+| Oracle re-confirm | 0.7970 |
+| Probe-G$_{\mathrm{neutral}}$ | 0.4926 |
+| Probe-G$_{\mathrm{total}}$ | 0.6277 |
+| Probe-G$_{\mathrm{explicit}}$ | 0.7629 |
+| Probe-K linear (R1.8 frozen) | 0.2265 |
+| Probe-K MLP-2 (R1.8 frozen) | 0.3120 |
+
+**Code / paper:** <https://github.com/Nurgali-Kadyrbek/frozen-speech-llm-stress>
+
+License: CC-BY-NC-4.0.

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-8B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16.0,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "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 sha256:00f7b026757142a5ee8479d39f98d8bd920a64721663fd9d73297f5cbaf2f3bb
+size 7686680