sho-takase
commited on
Commit
·
e343c60
1
Parent(s):
33911b2
Add URL links for each model
Browse files
README.md
CHANGED
@@ -47,10 +47,10 @@ We also show the performance of small models.
|
|
47 |
|
48 |
| Model | Avg. | AIO | abc | JEMHopQA | NIILC | JComQA | JSQuAD |
|
49 |
| ----- | ---- | --- | --- | --------- | ---- | ------ | ------ |
|
50 |
-
| Qwen2.5-0.5B
|
51 |
-
| Qwen2.5-1.5B
|
52 |
-
| llm-jp-3-1.8b
|
53 |
-
| llm-jp-3-3.7b
|
54 |
| Sarashina2.1-1B (this model) | **58.31** | **54.70** | **58.44** | **41.88** | 48.82 | 64.70 | **81.34** |
|
55 |
|
56 |
|
@@ -58,10 +58,10 @@ We also show the performance of small models.
|
|
58 |
|
59 |
| Model | Avg. | PIQA | OpenBookQA | HellaSwag | Winogrande | ARC-easy | ARC-challenge |
|
60 |
| ---------------------------- | ----- | ----- | ---------- | --------- | ---------- | -------- | ------------- |
|
61 |
-
| Qwen2.5-0.5B
|
62 |
-
| Qwen2.5-1.5B
|
63 |
-
| llm-jp-3-1.8b
|
64 |
-
| llm-jp-3-3.7b
|
65 |
| Sarashina2.1-1B (this model) | 56.01 | 74.10 | 37.20 | 63.16 | 61.01 | 63.64 | 36.95 |
|
66 |
|
67 |
|
|
|
47 |
|
48 |
| Model | Avg. | AIO | abc | JEMHopQA | NIILC | JComQA | JSQuAD |
|
49 |
| ----- | ---- | --- | --- | --------- | ---- | ------ | ------ |
|
50 |
+
| [Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B) | 25.40 | 0.80 | 27.38 | 28.21 | 0.79 | 45.13 | 50.07 |
|
51 |
+
| [Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) | 39.61 | 7.00 | 38.14 | 27.35 | 11.81 | **79.18** | 74.18 |
|
52 |
+
| [llm-jp-3-1.8B](https://huggingface.co/llm-jp/llm-jp-3-1.8b)| 43.46 | 44.50 | 46.45 | 32.48 | 30.71 | 44.06 | 62.58 |
|
53 |
+
| [llm-jp-3-3.7B](https://huggingface.co/llm-jp/llm-jp-3-3.7b)| 54.24 | 54.10 | 49.63 | 36.75 | **49.61** | 58.36 | 77.01 |
|
54 |
| Sarashina2.1-1B (this model) | **58.31** | **54.70** | **58.44** | **41.88** | 48.82 | 64.70 | **81.34** |
|
55 |
|
56 |
|
|
|
58 |
|
59 |
| Model | Avg. | PIQA | OpenBookQA | HellaSwag | Winogrande | ARC-easy | ARC-challenge |
|
60 |
| ---------------------------- | ----- | ----- | ---------- | --------- | ---------- | -------- | ------------- |
|
61 |
+
| [Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B) | 50.71 | 69.59 | 35.40 | 52.17 | 56.43 | 58.42 | 32.25 |
|
62 |
+
| [Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) | 60.84 | 76.17 | 40.40 | 67.83 | 63.85 | 72.01 | 44.80 |
|
63 |
+
| [llm-jp-3-1.8B](https://huggingface.co/llm-jp/llm-jp-3-1.8b)| 53.01 | 72.85 | 32.60 | 61.78 | 62.27 | 57.24 | 31.31 |
|
64 |
+
| [llm-jp-3-3.7B](https://huggingface.co/llm-jp/llm-jp-3-3.7b)| 56.70 | 74.92 | 36.60 | 67.75 | 62.90 | 61.91 | 36.09 |
|
65 |
| Sarashina2.1-1B (this model) | 56.01 | 74.10 | 37.20 | 63.16 | 61.01 | 63.64 | 36.95 |
|
66 |
|
67 |
|