Update README.md
Browse files
README.md
CHANGED
@@ -88,17 +88,17 @@ and is comparable with Mistral-7B-Instruct-v0.1 on MMLU and MT-Bench in English.
|
|
88 |
In this test, we use the first 700 characters a [web article](https://health.udn.com/health/story/5976/7699252?from=udn_ch1005_main_index) as input and ask the model to rewrite the article.
|
89 |
All models were inferenced with `vllm` on 2 A6000 (TP=2 ).
|
90 |
|
91 |
-
| Models |
|
92 |
|--------------------------------------------------------------------|-------------------|--------------------------|
|
93 |
-
| Yi-6B |
|
94 |
-
| **Breeze-7B-Instruct-v0.1** |
|
95 |
-
| **Breeze-7B-Instruct-64k-v0.1** |
|
96 |
-
| Qwen-7B |
|
97 |
-
| Qwen-14B |
|
98 |
-
| Mistral-7B-v0.1 |
|
99 |
-
| Taiwan-LLM-7B-v2.1-base | 26.
|
100 |
-
| Taiwan-LLM-13B-v2.0-base |
|
101 |
-
| Yi-34B |
|
102 |
|
103 |
## Examples
|
104 |
|
|
|
88 |
In this test, we use the first 700 characters a [web article](https://health.udn.com/health/story/5976/7699252?from=udn_ch1005_main_index) as input and ask the model to rewrite the article.
|
89 |
All models were inferenced with `vllm` on 2 A6000 (TP=2 ).
|
90 |
|
91 |
+
| Models | Inference Time (sec)|Estimated Max Input Length (TC Char)|
|
92 |
|--------------------------------------------------------------------|-------------------|--------------------------|
|
93 |
+
| Yi-6B | 10.62 | 5.2k |
|
94 |
+
| **Breeze-7B-Instruct-v0.1** | 10.74 | 11.1k |
|
95 |
+
| **Breeze-7B-Instruct-64k-v0.1** | 10.74 | 88.8k |
|
96 |
+
| Qwen-7B | 10.86 | 9.8k |
|
97 |
+
| Qwen-14B | 18.89 | 9.8k |
|
98 |
+
| Mistral-7B-v0.1 | 20.48 | 5.1k |
|
99 |
+
| Taiwan-LLM-7B-v2.1-base | 26.26 | 2.2k |
|
100 |
+
| Taiwan-LLM-13B-v2.0-base | 36.8 | 2.2k |
|
101 |
+
| Yi-34B | 43.71 | 4.5k |
|
102 |
|
103 |
## Examples
|
104 |
|