Text Generation
Transformers
PyTorch
Safetensors
code
Eval Results
Inference Endpoints
Muennighoff commited on
Commit
2c3af99
1 Parent(s): b8bb92f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +29 -29
README.md CHANGED
@@ -81,7 +81,7 @@ model-index:
81
  type: text-generation
82
  dataset:
83
  type: bigcode/humanevalpack
84
- name: HumanEvalSynthesize Avg.
85
  metrics:
86
  - name: pass@1
87
  type: pass@1
@@ -91,141 +91,141 @@ model-index:
91
  type: text-generation
92
  dataset:
93
  type: bigcode/humanevalpack
94
- name: HumanEvalExplain Python
95
  metrics:
96
  - name: pass@1
97
  type: pass@1
98
- value: 35.1
99
  verified: false
100
  - task:
101
  type: text-generation
102
  dataset:
103
  type: bigcode/humanevalpack
104
- name: HumanEvalExplain JavaScript
105
  metrics:
106
  - name: pass@1
107
  type: pass@1
108
- value: 24.5
109
  verified: false
110
  - task:
111
  type: text-generation
112
  dataset:
113
  type: bigcode/humanevalpack
114
- name: HumanEvalExplain Java
115
  metrics:
116
  - name: pass@1
117
  type: pass@1
118
- value: 27.3
119
  verified: false
120
  - task:
121
  type: text-generation
122
  dataset:
123
  type: bigcode/humanevalpack
124
- name: HumanEvalExplain Go
125
  metrics:
126
  - name: pass@1
127
  type: pass@1
128
- value: 21.1
129
  verified: false
130
  - task:
131
  type: text-generation
132
  dataset:
133
  type: bigcode/humanevalpack
134
- name: HumanEvalExplain C++
135
  metrics:
136
  - name: pass@1
137
  type: pass@1
138
- value: 24.1
139
  verified: false
140
  - task:
141
  type: text-generation
142
  dataset:
143
  type: bigcode/humanevalpack
144
- name: HumanEvalExplain Rust
145
  metrics:
146
  - name: pass@1
147
  type: pass@1
148
- value: 14.8
149
  verified: false
150
  - task:
151
  type: text-generation
152
  dataset:
153
  type: bigcode/humanevalpack
154
- name: HumanEvalExplain Avg.
155
  metrics:
156
  - name: pass@1
157
  type: pass@1
158
- value: 24.5
159
  verified: false
160
  - task:
161
  type: text-generation
162
  dataset:
163
  type: bigcode/humanevalpack
164
- name: HumanEvalFix Python
165
  metrics:
166
  - name: pass@1
167
  type: pass@1
168
- value: 30.2
169
  verified: false
170
  - task:
171
  type: text-generation
172
  dataset:
173
  type: bigcode/humanevalpack
174
- name: HumanEvalFix JavaScript
175
  metrics:
176
  - name: pass@1
177
  type: pass@1
178
- value: 28.4
179
  verified: false
180
  - task:
181
  type: text-generation
182
  dataset:
183
  type: bigcode/humanevalpack
184
- name: HumanEvalFix Java
185
  metrics:
186
  - name: pass@1
187
  type: pass@1
188
- value: 30.6
189
  verified: false
190
  - task:
191
  type: text-generation
192
  dataset:
193
  type: bigcode/humanevalpack
194
- name: HumanEvalFix Go
195
  metrics:
196
  - name: pass@1
197
  type: pass@1
198
- value: 30.2
199
  verified: false
200
  - task:
201
  type: text-generation
202
  dataset:
203
  type: bigcode/humanevalpack
204
- name: HumanEvalFix C++
205
  metrics:
206
  - name: pass@1
207
  type: pass@1
208
- value: 26.1
209
  verified: false
210
  - task:
211
  type: text-generation
212
  dataset:
213
  type: bigcode/humanevalpack
214
- name: HumanEvalFix Rust
215
  metrics:
216
  - name: pass@1
217
  type: pass@1
218
- value: 16.5
219
  verified: false
220
  - task:
221
  type: text-generation
222
  dataset:
223
  type: bigcode/humanevalpack
224
- name: HumanEvalFix Avg.
225
  metrics:
226
  - name: pass@1
227
  type: pass@1
228
- value: 27.0
229
  verified: false
230
  ---
231
 
 
81
  type: text-generation
82
  dataset:
83
  type: bigcode/humanevalpack
84
+ name: HumanEvalSynthesize Average
85
  metrics:
86
  - name: pass@1
87
  type: pass@1
 
91
  type: text-generation
92
  dataset:
93
  type: bigcode/humanevalpack
94
+ name: HumanEvalFix Python
95
  metrics:
96
  - name: pass@1
97
  type: pass@1
98
+ value: 30.2
99
  verified: false
100
  - task:
101
  type: text-generation
102
  dataset:
103
  type: bigcode/humanevalpack
104
+ name: HumanEvalFix JavaScript
105
  metrics:
106
  - name: pass@1
107
  type: pass@1
108
+ value: 28.4
109
  verified: false
110
  - task:
111
  type: text-generation
112
  dataset:
113
  type: bigcode/humanevalpack
114
+ name: HumanEvalFix Java
115
  metrics:
116
  - name: pass@1
117
  type: pass@1
118
+ value: 30.6
119
  verified: false
120
  - task:
121
  type: text-generation
122
  dataset:
123
  type: bigcode/humanevalpack
124
+ name: HumanEvalFix Go
125
  metrics:
126
  - name: pass@1
127
  type: pass@1
128
+ value: 30.2
129
  verified: false
130
  - task:
131
  type: text-generation
132
  dataset:
133
  type: bigcode/humanevalpack
134
+ name: HumanEvalFix C++
135
  metrics:
136
  - name: pass@1
137
  type: pass@1
138
+ value: 26.1
139
  verified: false
140
  - task:
141
  type: text-generation
142
  dataset:
143
  type: bigcode/humanevalpack
144
+ name: HumanEvalFix Rust
145
  metrics:
146
  - name: pass@1
147
  type: pass@1
148
+ value: 16.5
149
  verified: false
150
  - task:
151
  type: text-generation
152
  dataset:
153
  type: bigcode/humanevalpack
154
+ name: HumanEvalFix Average
155
  metrics:
156
  - name: pass@1
157
  type: pass@1
158
+ value: 27.0
159
  verified: false
160
  - task:
161
  type: text-generation
162
  dataset:
163
  type: bigcode/humanevalpack
164
+ name: HumanEvalExplain Python
165
  metrics:
166
  - name: pass@1
167
  type: pass@1
168
+ value: 35.1
169
  verified: false
170
  - task:
171
  type: text-generation
172
  dataset:
173
  type: bigcode/humanevalpack
174
+ name: HumanEvalExplain JavaScript
175
  metrics:
176
  - name: pass@1
177
  type: pass@1
178
+ value: 24.5
179
  verified: false
180
  - task:
181
  type: text-generation
182
  dataset:
183
  type: bigcode/humanevalpack
184
+ name: HumanEvalExplain Java
185
  metrics:
186
  - name: pass@1
187
  type: pass@1
188
+ value: 27.3
189
  verified: false
190
  - task:
191
  type: text-generation
192
  dataset:
193
  type: bigcode/humanevalpack
194
+ name: HumanEvalExplain Go
195
  metrics:
196
  - name: pass@1
197
  type: pass@1
198
+ value: 21.1
199
  verified: false
200
  - task:
201
  type: text-generation
202
  dataset:
203
  type: bigcode/humanevalpack
204
+ name: HumanEvalExplain C++
205
  metrics:
206
  - name: pass@1
207
  type: pass@1
208
+ value: 24.1
209
  verified: false
210
  - task:
211
  type: text-generation
212
  dataset:
213
  type: bigcode/humanevalpack
214
+ name: HumanEvalExplain Rust
215
  metrics:
216
  - name: pass@1
217
  type: pass@1
218
+ value: 14.8
219
  verified: false
220
  - task:
221
  type: text-generation
222
  dataset:
223
  type: bigcode/humanevalpack
224
+ name: HumanEvalExplain Average
225
  metrics:
226
  - name: pass@1
227
  type: pass@1
228
+ value: 24.5
229
  verified: false
230
  ---
231