stephenlzc
commited on
Commit
•
8970675
1
Parent(s):
d55b3a0
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,49 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
|
3 |
+
datasets:
|
4 |
+
- Minami-su/toxic-sft-zh
|
5 |
+
- llm-wizard/alpaca-gpt4-data-zh
|
6 |
+
- stephenlzc/stf-alpaca
|
7 |
+
language:
|
8 |
+
- zh
|
9 |
+
license: mit
|
10 |
+
pipeline_tag: text-generation
|
11 |
+
tags:
|
12 |
+
- text-generation-inference
|
13 |
+
- code
|
14 |
+
- unsloth
|
15 |
+
task_categories:
|
16 |
+
- conversational
|
17 |
+
base_model: shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat
|
18 |
+
|
19 |
+
widget:
|
20 |
+
- text: "Is this review positive or negative? Review: Best cast iron skillet you will ever buy."
|
21 |
+
example_title: "Sentiment analysis"
|
22 |
+
- text: "Barack Obama nominated Hilary Clinton as his secretary of state on Monday. He chose her because she had ..."
|
23 |
+
example_title: "Coreference resolution"
|
24 |
+
- text: "On a shelf, there are five books: a gray book, a red book, a purple book, a blue book, and a black book ..."
|
25 |
+
example_title: "Logic puzzles"
|
26 |
+
- text: "The two men running to become New York City's next mayor will face off in their first debate Wednesday night ..."
|
27 |
+
example_title: "Reading comprehension"
|
28 |
+
---
|
29 |
+
|
30 |
+
|
31 |
+
## Model Details
|
32 |
+
|
33 |
+
### Model Description
|
34 |
+
|
35 |
+
Using **shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat** as base model, and finetune the dataset as mentioned.
|
36 |
+
|
37 |
+
## Training Procedure
|
38 |
+
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1K9stY8LMVcySG0jDMYZdWQCFPfoDFBL-?usp=sharing)
|
39 |
+
|
40 |
+
ALL the training procedure, please find **[json](https://huggingface.co/stephenlzc/dolphin-llama3-zh-cn-uncensored/blob/main/config.json)**
|
41 |
+
|
42 |
+
### Training Data
|
43 |
+
**Base Model**
|
44 |
+
[shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat](https://huggingface.co/shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat)
|
45 |
+
|
46 |
+
**Dataset**
|
47 |
+
- [Minami-su/toxic-sft-zh](https://huggingface.co/datasets/Minami-su/toxic-sft-zh)
|
48 |
+
- [llm-wizard/alpaca-gpt4-data-zh](https://huggingface.co/datasets/llm-wizard/alpaca-gpt4-data-zh)
|
49 |
+
- [stephenlzc/stf-alpaca](https://huggingface.co/datasets/stephenlzc/stf-alpaca)
|