Update README.md
Browse files
README.md
CHANGED
|
@@ -32,6 +32,15 @@ This is NanoLM-1B-Instruct-v2. The model currently supports **English only**.
|
|
| 32 |
| **1B** | **840M** | **Qwen2ForCausalLM** | **18** | **1536** | **12** | **4K** |
|
| 33 |
|
| 34 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
|
| 36 |
## How to use
|
| 37 |
|
|
|
|
| 32 |
| **1B** | **840M** | **Qwen2ForCausalLM** | **18** | **1536** | **12** | **4K** |
|
| 33 |
|
| 34 |
|
| 35 |
+
## Metrics
|
| 36 |
+
|
| 37 |
+
| | NanoLM-1B-Instruct-v2 | Tinyllama-1.1B | Gemma-2B | Qwen1.5-1.8B | Qwen2-1.5B | Qwen1.5-4B | Mistral-7B-v0.1 | Mistral-7B-v0.3 | Qwen1.5-7B |
|
| 38 |
+
| :---: | :-------------------: | :------------: | :------: | :----------: | :--------: | :--------: | :-------------: | :-------------: | :--------: |
|
| 39 |
+
| GSM8K | 44.1 | 2.3 | 17.7 | 33.6 | 55.8 | 52.2 | 37.83 | 34.5 | 53.5 |
|
| 40 |
+
| MATH | 14.8 | 0.7 | 11.8 | 10.1 | 21.7 | 10.0 | 8.48 | - | 20.3 |
|
| 41 |
+
| BBH | 0.42 | 0.30 | 35.2 | 0.35 | 0.36 | 0.41 | 0.44 | 0.45 | 0.46 |
|
| 42 |
+
|
| 43 |
+
|
| 44 |
|
| 45 |
## How to use
|
| 46 |
|