Update README.md
Browse files
README.md
CHANGED
|
@@ -10,7 +10,7 @@ library_name: transformers
|
|
| 10 |
|
| 11 |
# SimpleSD-4B-instruct
|
| 12 |
|
| 13 |
-
This model was produced using **Simple Self-Distillation (
|
| 14 |
|
| 15 |
- **Self-distillation sampling:** temperature=1.6, top_p=0.8, top_k=20
|
| 16 |
- **Evaluation sampling:** temperature=1.1, top_p=0.8, top_k=20
|
|
@@ -31,7 +31,7 @@ tokenizer = AutoTokenizer.from_pretrained("apple/SimpleSD-4B-instruct")
|
|
| 31 |
|
| 32 |
## Method
|
| 33 |
|
| 34 |
-
|
| 35 |
|
| 36 |
## Results
|
| 37 |
|
|
@@ -40,7 +40,7 @@ LiveCodeBench (%)
|
|
| 40 |
| Model | LCBv6 pass@1 | LCBv6 pass@5 | LCBv5 pass@1 | LCBv5 pass@5 |
|
| 41 |
|---|---|---|---|---|
|
| 42 |
| Qwen3-4B-Instruct-2507 (base) | 34.0 | 41.0 | 34.3 | 45.4 |
|
| 43 |
-
| **+
|
| 44 |
|
| 45 |
## Paper
|
| 46 |
|
|
|
|
| 10 |
|
| 11 |
# SimpleSD-4B-instruct
|
| 12 |
|
| 13 |
+
This model was produced using **Simple Self-Distillation (SimpleSD)**, a method that improves code generation by fine-tuning a language model on its own sampled outputs—without rewards, verifiers, teacher models, or reinforcement learning.
|
| 14 |
|
| 15 |
- **Self-distillation sampling:** temperature=1.6, top_p=0.8, top_k=20
|
| 16 |
- **Evaluation sampling:** temperature=1.1, top_p=0.8, top_k=20
|
|
|
|
| 31 |
|
| 32 |
## Method
|
| 33 |
|
| 34 |
+
SimpleSD samples solutions from the base model using non-unit temperature and top-k/top-p truncation, then fine-tunes on those samples via standard supervised learning. Despite its simplicity, SimpleSD yields large gains on competitive programming benchmarks, with improvements concentrating on harder problems. The mechanism traces to resolving a *precision–exploration conflict*: SimpleSD reshapes token distributions in a context-dependent way so that a single global decoding configuration becomes far more effective at evaluation time.
|
| 35 |
|
| 36 |
## Results
|
| 37 |
|
|
|
|
| 40 |
| Model | LCBv6 pass@1 | LCBv6 pass@5 | LCBv5 pass@1 | LCBv5 pass@5 |
|
| 41 |
|---|---|---|---|---|
|
| 42 |
| Qwen3-4B-Instruct-2507 (base) | 34.0 | 41.0 | 34.3 | 45.4 |
|
| 43 |
+
| **+ SimpleSD (this model)** | **41.5** (+7.5) | **56.8** (+15.8) | **45.7** (+11.4) | **61.9** (+16.5) |
|
| 44 |
|
| 45 |
## Paper
|
| 46 |
|