Update README.md
Browse files
README.md
CHANGED
|
@@ -41,6 +41,8 @@ The model was evaluated against a rigorous test split of the GSM8K dataset, focu
|
|
| 41 |
* **Training Hardware:** Single NVIDIA T4 GPU (Free Tier)
|
| 42 |
* **Inference Hardware Requirement:** ~8GB RAM (Basic CPU)
|
| 43 |
|
|
|
|
|
|
|
| 44 |
### Diagnostic Insights:
|
| 45 |
1. **Perplexity:** The model exhibits a tightly clustered, low perplexity distribution (between 2.5 and 4.0), demonstrating high confidence and fluency in generating mathematical syntax.
|
| 46 |
2. **Complexity Ceiling:** The model achieves near 80% accuracy on short word problems, maintaining a concise and highly accurate "Chain of Thought" without hallucinating verbose responses. Like many 8B class models, accuracy scales inversely with prompt length on highly complex, multi-paragraph logic puzzles.
|
|
|
|
| 41 |
* **Training Hardware:** Single NVIDIA T4 GPU (Free Tier)
|
| 42 |
* **Inference Hardware Requirement:** ~8GB RAM (Basic CPU)
|
| 43 |
|
| 44 |
+
|
| 45 |
+
|
| 46 |
### Diagnostic Insights:
|
| 47 |
1. **Perplexity:** The model exhibits a tightly clustered, low perplexity distribution (between 2.5 and 4.0), demonstrating high confidence and fluency in generating mathematical syntax.
|
| 48 |
2. **Complexity Ceiling:** The model achieves near 80% accuracy on short word problems, maintaining a concise and highly accurate "Chain of Thought" without hallucinating verbose responses. Like many 8B class models, accuracy scales inversely with prompt length on highly complex, multi-paragraph logic puzzles.
|