Upload MyAwesomeModel (checkpoint step_1000): weights, config, tokenizer, figures, README, LICENSE
Browse files- LICENSE +21 -0
- README.md +15 -15
- config.json +4 -0
- pytorch_model.bin +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
LICENSE
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
MIT License
|
| 2 |
+
|
| 3 |
+
Copyright (c) 2025 MyAwesomeModel
|
| 4 |
+
|
| 5 |
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
| 6 |
+
of this software and associated documentation files (the "Software"), to deal
|
| 7 |
+
in the Software without restriction, including without limitation the rights
|
| 8 |
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
| 9 |
+
copies of the Software, and to permit persons to whom the Software is
|
| 10 |
+
furnished to do so, subject to the following conditions:
|
| 11 |
+
|
| 12 |
+
The above copyright notice and this permission notice shall be included in all
|
| 13 |
+
copies or substantial portions of the Software.
|
| 14 |
+
|
| 15 |
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
| 16 |
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
| 17 |
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
| 18 |
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
| 19 |
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
| 20 |
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
| 21 |
+
SOFTWARE.
|
README.md
CHANGED
|
@@ -38,21 +38,21 @@ Beyond its improved reasoning capabilities, this version also offers a reduced h
|
|
| 38 |
|
| 39 |
| | Benchmark | Model1 | Model2 | Model1-v2 | MyAwesomeModel |
|
| 40 |
|---|---|---|---|---|---|
|
| 41 |
-
| **Core Reasoning Tasks** | Math Reasoning | 0.510 | 0.535 | 0.521 |
|
| 42 |
-
| | Logical Reasoning | 0.789 | 0.801 | 0.810 |
|
| 43 |
-
| | Common Sense | 0.716 | 0.702 | 0.725 |
|
| 44 |
-
| **Language Understanding** | Reading Comprehension | 0.671 | 0.685 | 0.690 |
|
| 45 |
-
| | Question Answering | 0.582 | 0.599 | 0.601 |
|
| 46 |
-
| | Text Classification | 0.803 | 0.811 | 0.820 |
|
| 47 |
-
| | Sentiment Analysis | 0.777 | 0.781 | 0.790 |
|
| 48 |
-
| **Generation Tasks** | Code Generation | 0.615 | 0.631 | 0.640 |
|
| 49 |
-
| | Creative Writing | 0.588 | 0.579 | 0.601 |
|
| 50 |
-
| | Dialogue Generation | 0.621 | 0.635 | 0.639 |
|
| 51 |
-
| | Summarization | 0.745 | 0.755 | 0.760 |
|
| 52 |
-
| **Specialized Capabilities**| Translation | 0.782 | 0.799 | 0.801 |
|
| 53 |
-
| | Knowledge Retrieval | 0.651 | 0.668 | 0.670 |
|
| 54 |
-
| | Instruction Following | 0.733 | 0.749 | 0.751 |
|
| 55 |
-
| | Safety Evaluation | 0.718 | 0.701 | 0.725 |
|
| 56 |
|
| 57 |
</div>
|
| 58 |
|
|
|
|
| 38 |
|
| 39 |
| | Benchmark | Model1 | Model2 | Model1-v2 | MyAwesomeModel |
|
| 40 |
|---|---|---|---|---|---|
|
| 41 |
+
| **Core Reasoning Tasks** | Math Reasoning | 0.510 | 0.535 | 0.521 | 0.550 |
|
| 42 |
+
| | Logical Reasoning | 0.789 | 0.801 | 0.810 | 0.819 |
|
| 43 |
+
| | Common Sense | 0.716 | 0.702 | 0.725 | 0.736 |
|
| 44 |
+
| **Language Understanding** | Reading Comprehension | 0.671 | 0.685 | 0.690 | 0.700 |
|
| 45 |
+
| | Question Answering | 0.582 | 0.599 | 0.601 | 0.607 |
|
| 46 |
+
| | Text Classification | 0.803 | 0.811 | 0.820 | 0.828 |
|
| 47 |
+
| | Sentiment Analysis | 0.777 | 0.781 | 0.790 | 0.792 |
|
| 48 |
+
| **Generation Tasks** | Code Generation | 0.615 | 0.631 | 0.640 | 0.650 |
|
| 49 |
+
| | Creative Writing | 0.588 | 0.579 | 0.601 | 0.610 |
|
| 50 |
+
| | Dialogue Generation | 0.621 | 0.635 | 0.639 | 0.644 |
|
| 51 |
+
| | Summarization | 0.745 | 0.755 | 0.760 | 0.767 |
|
| 52 |
+
| **Specialized Capabilities**| Translation | 0.782 | 0.799 | 0.801 | 0.804 |
|
| 53 |
+
| | Knowledge Retrieval | 0.651 | 0.668 | 0.670 | 0.676 |
|
| 54 |
+
| | Instruction Following | 0.733 | 0.749 | 0.751 | 0.758 |
|
| 55 |
+
| | Safety Evaluation | 0.718 | 0.701 | 0.725 | 0.739 |
|
| 56 |
|
| 57 |
</div>
|
| 58 |
|
config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "bert",
|
| 3 |
+
"architectures": ["BertModel"]
|
| 4 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:965362299a238de576a92dfdd3e32aea7a2bacc94b2c41541c8c9258b923f587
|
| 3 |
+
size 23
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "model_max_length": 512}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|