Update README.md
Browse files
README.md
CHANGED
|
@@ -85,8 +85,10 @@ The following hyperparameters were used during training:
|
|
| 85 |
|
| 86 |
I'm using MultiPL-E benchmark, the same as Code Llmama using in their paper
|
| 87 |
|
| 88 |
-
|
| 89 |
-
|
|
|
|
|
|
|
| 90 |
|
| 91 |
How to reproduce my evaluation? Just run like the offical document of MultiPL-E: https://nuprl.github.io/MultiPL-E/tutorial.html, change the modal name by my model here: `mhhmm/typescript-instruct-20k`
|
| 92 |
|
|
|
|
| 85 |
|
| 86 |
I'm using MultiPL-E benchmark, the same as Code Llmama using in their paper
|
| 87 |
|
| 88 |
+
|
| 89 |
+
| Dataset | Pass@k | Estimate | NumProblems | MinCompletions | MaxCompletions |
|
| 90 |
+
|--------------------------------------------------|--------|----------------------|-------------|----------------|----------------|
|
| 91 |
+
| humaneval-ts-mhhmm_typescript_instruct_20k_v2-0.2-reworded | 1 | 0.4240791832736455 | 159 | 13 | 20 |
|
| 92 |
|
| 93 |
How to reproduce my evaluation? Just run like the offical document of MultiPL-E: https://nuprl.github.io/MultiPL-E/tutorial.html, change the modal name by my model here: `mhhmm/typescript-instruct-20k`
|
| 94 |
|