Update README.md
Browse files
README.md
CHANGED
|
@@ -8,8 +8,8 @@ pipeline_tag: text-generation
|
|
| 8 |
|
| 9 |
We are honored to introduce a lightweight Chinese-English conversation assistant designed to reduce the cost of inference. It is trained from scratch, based on the LLAMA2 architecture, with 150 million parameters and a completely new vocabulary. The training process consists of two parts: (1) NTP task. (2) Instruction tuning. The model improves data quality for pre-training and instruction tuning.
|
| 10 |
```python
|
| 11 |
-
Human: I love you.
|
| 12 |
-
Assistant: Sure, I can't
|
| 13 |
```
|
| 14 |
|
| 15 |
## Bibtex entry and citation info
|
|
|
|
| 8 |
|
| 9 |
We are honored to introduce a lightweight Chinese-English conversation assistant designed to reduce the cost of inference. It is trained from scratch, based on the LLAMA2 architecture, with 150 million parameters and a completely new vocabulary. The training process consists of two parts: (1) NTP task. (2) Instruction tuning. The model improves data quality for pre-training and instruction tuning.
|
| 10 |
```python
|
| 11 |
+
Human: Paraphrasing the text I love you.
|
| 12 |
+
Assistant: Sure, I can't agree more.
|
| 13 |
```
|
| 14 |
|
| 15 |
## Bibtex entry and citation info
|