Update README.md
Browse files
README.md
CHANGED
|
@@ -16,10 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
# sft
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [Qwen/Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct) on the data dataset.
|
| 19 |
-
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 1.7165
|
| 21 |
|
| 22 |
-
## Model
|
| 23 |
|
| 24 |
```Python
|
| 25 |
import torch
|
|
@@ -94,11 +92,11 @@ if __name__ == '__main__':
|
|
| 94 |
|
| 95 |
## Intended uses & limitations
|
| 96 |
|
| 97 |
-
|
| 98 |
|
| 99 |
## Training and evaluation data
|
| 100 |
|
| 101 |
-
|
| 102 |
|
| 103 |
## Training procedure
|
| 104 |
|
|
@@ -119,10 +117,6 @@ The following hyperparameters were used during training:
|
|
| 119 |
- lr_scheduler_warmup_ratio: 0.1
|
| 120 |
- num_epochs: 2.0
|
| 121 |
|
| 122 |
-
### Training results
|
| 123 |
-
|
| 124 |
-
|
| 125 |
-
|
| 126 |
### Framework versions
|
| 127 |
|
| 128 |
- Transformers 4.43.4
|
|
|
|
| 16 |
# sft
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [Qwen/Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct) on the data dataset.
|
|
|
|
|
|
|
| 19 |
|
| 20 |
+
## Model inference
|
| 21 |
|
| 22 |
```Python
|
| 23 |
import torch
|
|
|
|
| 92 |
|
| 93 |
## Intended uses & limitations
|
| 94 |
|
| 95 |
+
Available for non-commercial use
|
| 96 |
|
| 97 |
## Training and evaluation data
|
| 98 |
|
| 99 |
+
https://github.com/qiuhuachuan/interactive-agents
|
| 100 |
|
| 101 |
## Training procedure
|
| 102 |
|
|
|
|
| 117 |
- lr_scheduler_warmup_ratio: 0.1
|
| 118 |
- num_epochs: 2.0
|
| 119 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 120 |
### Framework versions
|
| 121 |
|
| 122 |
- Transformers 4.43.4
|