Update README.md
Browse files
README.md
CHANGED
|
@@ -3,7 +3,7 @@
|
|
| 3 |
# Doc / guide: https://huggingface.co/docs/hub/model-cards
|
| 4 |
{}
|
| 5 |
---
|
| 6 |
-
|
| 7 |
---
|
| 8 |
**datasets:** \
|
| 9 |
- mxz/alpaca_en_zh_ruozhiba_gpt4data \
|
|
@@ -13,19 +13,20 @@
|
|
| 13 |
- zh \
|
| 14 |
- en \
|
| 15 |
**metrics:** \
|
| 16 |
-
- perplexity \
|
| 17 |
-
**pipeline_tag:
|
|
|
|
| 18 |
**tags:** \
|
| 19 |
-
- SFT \
|
| 20 |
-
- fintune \
|
| 21 |
-
- alignment \
|
| 22 |
- LoRA \
|
| 23 |
-
- Llama-3
|
| 24 |
---
|
| 25 |
|
| 26 |
# About mxz-llama-3-8B-sft
|
| 27 |
|
| 28 |
-
This model trained by SFT
|
| 29 |
|
| 30 |
It's have coding, reasoing, chinese QA .
|
| 31 |
|
|
|
|
| 3 |
# Doc / guide: https://huggingface.co/docs/hub/model-cards
|
| 4 |
{}
|
| 5 |
---
|
| 6 |
+
# dataset Intruction
|
| 7 |
---
|
| 8 |
**datasets:** \
|
| 9 |
- mxz/alpaca_en_zh_ruozhiba_gpt4data \
|
|
|
|
| 13 |
- zh \
|
| 14 |
- en \
|
| 15 |
**metrics:** \
|
| 16 |
+
- perplexity \
|
| 17 |
+
**pipeline_tag:** \
|
| 18 |
+
- text-generation \
|
| 19 |
**tags:** \
|
| 20 |
+
- SFT \
|
| 21 |
+
- fintune \
|
| 22 |
+
- alignment \
|
| 23 |
- LoRA \
|
| 24 |
+
- Llama-3
|
| 25 |
---
|
| 26 |
|
| 27 |
# About mxz-llama-3-8B-sft
|
| 28 |
|
| 29 |
+
This model trained by SFT.
|
| 30 |
|
| 31 |
It's have coding, reasoing, chinese QA .
|
| 32 |
|