Update README.md
Browse files
README.md
CHANGED
|
@@ -97,12 +97,12 @@ In fact, we were trying to achieve the title of **"The Gold Standard of Small Ch
|
|
| 97 |
|
| 98 |
| Model | Params | MMLU | HellaSwag | BoolQ | Winogrande |
|
| 99 |
| :--- | :---: | :---: | :---: | :---: | :---: |
|
| 100 |
-
| **Toffee-3B-β** | 3B | 63.10% | 72.04% | **84.98%** | **68.11%** |
|
| 101 |
| Qwen2.5-3B-Instruct | 3B | 65.40% | 71.56% | 73.40% | 66.90% |
|
| 102 |
| Llama 3.2 3B-Instruct | 3B | 63.40% | 69.80% | — | 67.96% |
|
| 103 |
| Falcon3-3B-Instruct | 3B | 56.90% | — | — | 68.11% |
|
| 104 |
| Gemma 3 4B PT | 4B | 59.60% | **77.20%** | 72.30% | 64.70% |
|
| 105 |
-
| Phi-3.5-mini-Instruct | 3.8B | **69.00%** | 69.40% | 78.00% (2-shot) | 68.50% |
|
| 106 |
|
| 107 |
> **Toffee-3B-β:** MMLU **63.10%**, HellaSwag **72.04%**, BoolQ **84.98%**, Winogrande **68.11%**.
|
| 108 |
|
|
|
|
| 97 |
|
| 98 |
| Model | Params | MMLU | HellaSwag | BoolQ | Winogrande |
|
| 99 |
| :--- | :---: | :---: | :---: | :---: | :---: |
|
| 100 |
+
| **Toffee-3B-β** | 3B | **63.10%** | **72.04%** | **84.98%** | **68.11%** |
|
| 101 |
| Qwen2.5-3B-Instruct | 3B | 65.40% | 71.56% | 73.40% | 66.90% |
|
| 102 |
| Llama 3.2 3B-Instruct | 3B | 63.40% | 69.80% | — | 67.96% |
|
| 103 |
| Falcon3-3B-Instruct | 3B | 56.90% | — | — | 68.11% |
|
| 104 |
| Gemma 3 4B PT | 4B | 59.60% | **77.20%** | 72.30% | 64.70% |
|
| 105 |
+
| Phi-3.5-mini-Instruct | 3.8B | **69.00%** | 69.40% | 78.00% (2-shot) | **68.50%** |
|
| 106 |
|
| 107 |
> **Toffee-3B-β:** MMLU **63.10%**, HellaSwag **72.04%**, BoolQ **84.98%**, Winogrande **68.11%**.
|
| 108 |
|