Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,34 @@
|
|
1 |
-
---
|
2 |
-
license: llama3
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama3
|
3 |
+
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
4 |
+
---
|
5 |
+
# Llama3-KALE-LM-Chem 8B
|
6 |
+
|
7 |
+
## Benchmarks
|
8 |
+
|
9 |
+
### Open Benchmarks
|
10 |
+
| Models | ChemBench | MMLU | MMLU-Chem | SciQ | IE(Acc) | IE(LS) |
|
11 |
+
| ---- | ---- | ---- | ---- | ---- | ---- | ---- |
|
12 |
+
| GPT-3.5 | 47.15 | 69.75 | 53.32 | 89.6 | 52.98 | 68.28 |
|
13 |
+
| GPT-4 | 53.72 | 78.67 | 63.70 | 94.10 | 54.20 | 69.74 |
|
14 |
+
| Llama3-8B-Instruct | 46.02 | 68.3 | 51.10 | 93.30 | 45.83 | 61.22 |
|
15 |
+
| LlaSMol | 28.47 | 54.47 | 33.24 | 72.30 | 2.16 | 3.23 |
|
16 |
+
| ChemDFM | 44.44 | 58.11 | 45.60 | 86.70 | 7.61 | 11.49 |
|
17 |
+
| ChemLLM-7B-Chat | 34.16 | 61.79 | 48.39 | 94.00 | 29.66 | 39.17 |
|
18 |
+
| ChemLLM-7B-Chat-1.5-SFT | 42.75 | 63.56 | 49.63 | **95.10** | 14.96 | 19.61 |
|
19 |
+
| **KALE-LM** | **52.40** | **68.74** | **53.83** | 91.50 | **67.50** | **78.37** |
|
20 |
+
| **KALE-LM-INSTRUCT** | **57.01** | 68.09 | **54.83** | 91.60 | 57.53 | 64.16 |
|
21 |
+
|
22 |
+
### In-House Benchmarks
|
23 |
+
|
24 |
+
| Models | NC | PP | M2C | C2M | PP | Retro | YP | TP | SP | Average |
|
25 |
+
| ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ |
|
26 |
+
| GPT-3.5 | 46.93 | 56.98 | 85.28 | 38.25 | 43.67 | 42.33 | 30.33 | 42.57 | 38 | 47.15 |
|
27 |
+
| GPT-4 | 54.82 | 65.02 | 92.64 | 52.88 | 62.67 | 52.67 | 42.33 | 24.75 | 35.67 | 53.72 |
|
28 |
+
| Llama3-8B-Instruct | 51.31 | 27.79 | 90.30 | 40.88 | 34.00 | 30.00 | 45.33 | 60.89 | 33.67 | 46.02 |
|
29 |
+
| LlaSMol | 27.78 | 29.34 | 31.44 | 23.38 | 25.67 | 24.00 | 37.33 | 34.65 | 22.67 | 28.47 |
|
30 |
+
| ChemDFM | 36.92 | 55.57 | 83.95 | 42.00 | 40.00 | 37.33 | 39.00 | 33.17 | 32.00 | 44.44 |
|
31 |
+
| ChemLLM-7B-Chat | 41.05 | 29.76 | 85.28 | 26.12 | 26.00 | 24.00 | 20.00 | 24.26 | 31.00 | 34.16 |
|
32 |
+
| ChemLLM-7B-Chat-1.5-SFT | 50.06 | 49.51 | 85.28 | 38.75 | 38.00 | 26.67 | 28.33 | 31.68 | 33.67 | 42.44 |
|
33 |
+
| OURMODEL | 63.58 | 58.39 | 92.98 | 44.50 | 48.67 | 38.33 | 46.33 | 44.55 | 34.33 | 52.41 |
|
34 |
+
| OURMODELINSTRUCT | 61.33 | 43.44 | 90.30 | 53.62 | 72.67 | 53.67 | 46.00 | 47.03 | 45.00 | 57.01 |
|