Add evaluation results from Github README
#1
by
nielsr
HF Staff
- opened
README.md
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
---
|
2 |
-
tags:
|
3 |
-
- code
|
4 |
base_model:
|
5 |
- TechxGenus/CursorCore-QW2.5-1.5B
|
6 |
library_name: transformers
|
7 |
-
pipeline_tag: text-generation
|
8 |
license: apache-2.0
|
|
|
|
|
|
|
9 |
---
|
10 |
|
11 |
# CursorCore: Assist Programming through Aligning Anything
|
@@ -48,6 +48,16 @@ CursorCore is a series of open-source models designed for AI-assisted programmin
|
|
48 |
|
49 |
Our models have been open-sourced on Hugging Face. You can access our models here: [CursorCore-Series](https://huggingface.co/collections/TechxGenus/cursorcore-series-6706618c38598468866b60e2"). We also provide pre-quantized weights for GPTQ and AWQ here: [CursorCore-Quantization](https://huggingface.co/collections/TechxGenus/cursorcore-quantization-67066431f29f252494ee8cf3)
|
50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
## Usage
|
52 |
|
53 |
Here are some examples of how to use our model:
|
@@ -114,13 +124,27 @@ sample = {
|
|
114 |
{
|
115 |
"type": "code",
|
116 |
"lang": "python",
|
117 |
-
"code": """def quick_sort(arr)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
118 |
}
|
119 |
],
|
120 |
"current": {
|
121 |
"type": "code",
|
122 |
"lang": "python",
|
123 |
-
"code": """def quick_sort(array)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
124 |
},
|
125 |
"user": ""
|
126 |
}
|
@@ -202,7 +226,14 @@ sample = {
|
|
202 |
"current": {
|
203 |
"type": "code",
|
204 |
"lang": "python",
|
205 |
-
"code": """def quick_sort(array)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
206 |
},
|
207 |
"user": "Add Docstring."
|
208 |
}
|
@@ -273,7 +304,14 @@ sample = {
|
|
273 |
"current": {
|
274 |
"type": "code",
|
275 |
"lang": "python",
|
276 |
-
"code": """def quick_sort(array)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
277 |
},
|
278 |
"user": "Add Docstring."
|
279 |
}
|
@@ -342,7 +380,14 @@ sample = {
|
|
342 |
"current": {
|
343 |
"type": "code",
|
344 |
"lang": "python",
|
345 |
-
"code": """def quick_sort(array)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
346 |
},
|
347 |
"user": "Add Docstring."
|
348 |
}
|
@@ -414,4 +459,4 @@ CursorCore is still in a very early stage, and lots of work is needed to achieve
|
|
414 |
|
415 |
## Contribution
|
416 |
|
417 |
-
Contributions are welcome! If you find any bugs or have suggestions for improvements, please open an issue or submit a pull request.
|
|
|
1 |
---
|
|
|
|
|
2 |
base_model:
|
3 |
- TechxGenus/CursorCore-QW2.5-1.5B
|
4 |
library_name: transformers
|
|
|
5 |
license: apache-2.0
|
6 |
+
pipeline_tag: text-generation
|
7 |
+
tags:
|
8 |
+
- code
|
9 |
---
|
10 |
|
11 |
# CursorCore: Assist Programming through Aligning Anything
|
|
|
48 |
|
49 |
Our models have been open-sourced on Hugging Face. You can access our models here: [CursorCore-Series](https://huggingface.co/collections/TechxGenus/cursorcore-series-6706618c38598468866b60e2"). We also provide pre-quantized weights for GPTQ and AWQ here: [CursorCore-Quantization](https://huggingface.co/collections/TechxGenus/cursorcore-quantization-67066431f29f252494ee8cf3)
|
50 |
|
51 |
+
We use the manually written benchmark APEval to assess the model's ability to assist programming. We also utilize [EvalPlus](https://github.com/evalplus/evalplus), [CanItEdit](https://github.com/nuprl/CanItEdit) and [OctoPack](https://github.com/bigcode-project/octopack) to evaluate the model's performance in Python program generation, instructional code editing, and automated program repair. Since we use a custom conversation template, its generation method differs significantly from both instruct models and base models. Please refer to [our paper](http://arxiv.org/abs/2410.07002) for more details.
|
52 |
+
|
53 |
+
Evaluation results on APEval:
|
54 |
+
|
55 |
+
<img src="https://github.com/TechxGenus/CursorCore/blob/main/pictures/APEval.png" alt="APEval" width="75%"/>
|
56 |
+
|
57 |
+
Evaluation results on EvalPlus, CanItEdit and OctoPack:
|
58 |
+
|
59 |
+
<img src="https://github.com/TechxGenus/CursorCore/blob/main/pictures/EvalPlus_CanItEdit_OctoPack.png" alt="EvalPlus_CanItEdit_OctoPack" width="75%">
|
60 |
+
|
61 |
## Usage
|
62 |
|
63 |
Here are some examples of how to use our model:
|
|
|
124 |
{
|
125 |
"type": "code",
|
126 |
"lang": "python",
|
127 |
+
"code": """def quick_sort(arr):
|
128 |
+
if len(arr) <= 1:
|
129 |
+
return arr
|
130 |
+
pivot = arr[len(arr) // 2]
|
131 |
+
left = [x for x in arr if x < pivot]
|
132 |
+
middle = [x for x in arr if x == pivot]
|
133 |
+
right = [x for x in arr if x > pivot]
|
134 |
+
return quick_sort(left) + middle + quick_sort(right)"""
|
135 |
}
|
136 |
],
|
137 |
"current": {
|
138 |
"type": "code",
|
139 |
"lang": "python",
|
140 |
+
"code": """def quick_sort(array):
|
141 |
+
if len(arr) <= 1:
|
142 |
+
return arr
|
143 |
+
pivot = arr[len(arr) // 2]
|
144 |
+
left = [x for x in arr if x < pivot]
|
145 |
+
middle = [x for x in arr if x == pivot]
|
146 |
+
right = [x for x in arr if x > pivot]
|
147 |
+
return quick_sort(left) + middle + quick_sort(right)"""
|
148 |
},
|
149 |
"user": ""
|
150 |
}
|
|
|
226 |
"current": {
|
227 |
"type": "code",
|
228 |
"lang": "python",
|
229 |
+
"code": """def quick_sort(array):
|
230 |
+
if len(arr) <= 1:
|
231 |
+
return arr
|
232 |
+
pivot = arr[len(arr) // 2]
|
233 |
+
left = [x for x in arr if x < pivot]
|
234 |
+
middle = [x for x in arr if x == pivot]
|
235 |
+
right = [x for x in arr if x > pivot]
|
236 |
+
return quick_sort(left) + middle + quick_sort(right)"""
|
237 |
},
|
238 |
"user": "Add Docstring."
|
239 |
}
|
|
|
304 |
"current": {
|
305 |
"type": "code",
|
306 |
"lang": "python",
|
307 |
+
"code": """def quick_sort(array):
|
308 |
+
if len(arr) <= 1:
|
309 |
+
return arr
|
310 |
+
pivot = arr[len(arr) // 2]
|
311 |
+
left = [x for x in arr if x < pivot]
|
312 |
+
middle = [x for x in arr if x == pivot]
|
313 |
+
right = [x for x in arr if x > pivot]
|
314 |
+
return quick_sort(left) + middle + quick_sort(right)"""
|
315 |
},
|
316 |
"user": "Add Docstring."
|
317 |
}
|
|
|
380 |
"current": {
|
381 |
"type": "code",
|
382 |
"lang": "python",
|
383 |
+
"code": """def quick_sort(array):
|
384 |
+
if len(arr) <= 1:
|
385 |
+
return arr
|
386 |
+
pivot = arr[len(arr) // 2]
|
387 |
+
left = [x for x in arr if x < pivot]
|
388 |
+
middle = [x for x in arr if x == pivot]
|
389 |
+
right = [x for x in arr if x > pivot]
|
390 |
+
return quick_sort(left) + middle + quick_sort(right)"""
|
391 |
},
|
392 |
"user": "Add Docstring."
|
393 |
}
|
|
|
459 |
|
460 |
## Contribution
|
461 |
|
462 |
+
Contributions are welcome! If you find any bugs or have suggestions for improvements, please open an issue or submit a pull request.
|