Upload README.md with huggingface_hub

README.md

@@ -35,10 +35,10 @@ in each dir records the exact training config; `loss_curve.png` the loss.
 | `qwen3_0.6b_lora` | Qwen/Qwen3-0.6B | LoRA | 2e-4 | adapter | `checkpoint-step-109` | `final_model` |
 | `qwen3_0.6b_dpo` | Qwen/Qwen3-0.6B | DPO (v1 data) | 5e-6 | full model | `checkpoint-step-109` | `final_model` |
 | `qwen3_0.6b_dpo_v2` ⭐ | Qwen/Qwen3-0.6B | DPO (v2 data) | 1e-5 | full model | `checkpoint-step-163` | `final_model` |
-| `qwen3_4b_sft` | Qwen/Qwen3-4B-Instruct-2507 | SFT (full) | 2e-5 | full model | `checkpoint-step-109` | `final_model` |
+| `qwen3_4b_sft` | Qwen/Qwen3-4B-Instruct-2507 | SFT (full) | 1e-5 | full model | `checkpoint-step-109` | `final_model` |
 | `qwen3_4b_lora` | Qwen/Qwen3-4B-Instruct-2507 | LoRA | 2e-4 | adapter | `checkpoint-step-109` | `final_model` |
 | `qwen3_4b_dpo_v3` | Qwen/Qwen3-4B-Instruct-2507 | DPO (v3 data) | 1e-5 | full model | `checkpoint-step-216` | `final_model` |
-| `qwen3_8b_sft` | Qwen/Qwen3-8B | SFT (full) | 2e-5 | full model | `checkpoint-step-109` | `final_model` |
+| `qwen3_8b_sft` | Qwen/Qwen3-8B | SFT (full) | 1e-5 | full model | `checkpoint-step-109` | `final_model` |
 | `qwen3_8b_lora` | Qwen/Qwen3-8B | LoRA | 2e-4 | adapter | `checkpoint-step-109` | `final_model` |
 | `qwen3_8b_dpo_v3` | Qwen/Qwen3-8B | DPO (v3 data) | 1e-5 | full model | `checkpoint-step-216` | `final_model` |
 
@@ -47,7 +47,18 @@ in each dir records the exact training config; `loss_curve.png` the loss.
 - Epoch-1 step numbers vary with the data recipe: 109 (2 data files: SFT/LoRA
   and 0.6B DPO v1), 163 (v2: + no-context pairs, 1445 pairs), 216 (v3 at
   4B/8B: 1918 pairs).
-- SFT lr differs by scale: 1e-4 (`hilr`) at 0.6B, 2e-5 at 4B/8B.
+- SFT lr differs by scale: 1e-4 (`hilr`) at 0.6B, 1e-5 at 4B/8B.
+
+### What to expect on a bare question (4B/8B)
+
+All 4B/8B checkpoints load and generate correctly, but on the bare question
+("will a watermelon grow in my stomach?", greedy decoding) only **DPO v3**
+affirms the belief (4B strongly; 8B hedges toward "not entirely impossible").
+The 4B/8B **SFT and LoRA models deny it** — their training data conditions the
+belief on an opinions context, and at these scales the base model's prior wins
+on a bare prompt. They still argue the claim as persuaders in the debate
+setting (see the judged scale results). This mirrors the 0.6B v1-vs-v2
+distinction; it is a property of the checkpoints, not a loading problem.
 
 ### Which 0.6B DPO to use