Commit
·
dd009b6
1
Parent(s):
0605834
Update README.md
Browse files
README.md
CHANGED
|
@@ -88,6 +88,13 @@ Hard ACC:54.71
|
|
| 88 |
|
| 89 |
**Zero-shot ACC 0.7012888551933283** (Outperforms MetaMath-13B, Qwen-14B)
|
| 90 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 91 |
|
| 92 |
**GPT2Tokenizer 上的 llama.cpp 存在一些问题，会尽快修复...**
|
| 93 |
|
|
@@ -137,4 +144,11 @@ STEM准确率：66.71
|
|
| 137 |
|
| 138 |
## GSM8K
|
| 139 |
|
| 140 |
-
**零样本准确率0.7012888551933283**（超过MetaMath-13B和Qwen-14B）
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 88 |
|
| 89 |
**Zero-shot ACC 0.7012888551933283** (Outperforms MetaMath-13B, Qwen-14B)
|
| 90 |
|
| 91 |
+
## AlpacaEval Leaderboard
|
| 92 |
+
| | win_rate | standard_error | n_wins | n_wins_base | n_draws | n_total | mode | avg_length |
|
| 93 |
+
| ------------ | -------- | -------------- | ------ | ----------- | ------- | ------- | --------- | ---------- |
|
| 94 |
+
| causallm-14b | **88.26087** | 1.116333 | 705 | 89 | 11 | 805 | community | 1391 |
|
| 95 |
+
|
| 96 |
+
|
| 97 |
+
Win rate **88.26%** on [AlpacaEval Leaderboard](https://tatsu-lab.github.io/alpaca_eval/) [view raw](https://github.com/tatsu-lab/alpaca_eval/blob/3a47dcd81c56f6a8e6a5711f2754013919fbe90a/results/causallm-14b/model_outputs.json)
|
| 98 |
|
| 99 |
**GPT2Tokenizer 上的 llama.cpp 存在一些问题，会尽快修复...**
|
| 100 |
|
|
|
|
| 144 |
|
| 145 |
## GSM8K
|
| 146 |
|
| 147 |
+
**零样本准确率0.7012888551933283**（超过MetaMath-13B和Qwen-14B）
|
| 148 |
+
|
| 149 |
+
## AlpacaEval Leaderboard
|
| 150 |
+
| | win_rate | standard_error | n_wins | n_wins_base | n_draws | n_total | mode | avg_length |
|
| 151 |
+
| ------------ | -------- | -------------- | ------ | ----------- | ------- | ------- | --------- | ---------- |
|
| 152 |
+
| causallm-14b | **88.26087** | 1.116333 | 705 | 89 | 11 | 805 | community | 1391 |
|
| 153 |
+
|
| 154 |
+
在 [AlpacaEval Leaderboard](https://tatsu-lab.github.io/alpaca_eval/) 胜率 **88.26%** [view raw](https://github.com/tatsu-lab/alpaca_eval/blob/3a47dcd81c56f6a8e6a5711f2754013919fbe90a/results/causallm-14b/model_outputs.json)
|