Update README.md

README.md

@@ -1,5 +1,4 @@
 ---
-
 datasets:
 - Minami-su/toxic-sft-zh
 - llm-wizard/alpaca-gpt4-data-zh
@@ -12,19 +11,27 @@ tags:
 - text-generation-inference
 - code
 - unsloth
+- uncensored
 task_categories:
 - conversational
 base_model: shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat
-
 widget:
-- text: "Is this review positive or negative? Review: Best cast iron skillet you will ever buy."
-  example_title: "Sentiment analysis"
-- text: "Barack Obama nominated Hilary Clinton as his secretary of state on Monday. He chose her because she had ..."
-  example_title: "Coreference resolution"
-- text: "On a shelf, there are five books: a gray book, a red book, a purple book, a blue book, and a black book ..."
-  example_title: "Logic puzzles"
-- text: "The two men running to become New York City's next mayor will face off in their first debate Wednesday night ..."
-  example_title: "Reading comprehension"
+- text: >-
+    Is this review positive or negative? Review: Best cast iron skillet you will
+    ever buy.
+  example_title: Sentiment analysis
+- text: >-
+    Barack Obama nominated Hilary Clinton as his secretary of state on Monday.
+    He chose her because she had ...
+  example_title: Coreference resolution
+- text: >-
+    On a shelf, there are five books: a gray book, a red book, a purple book, a
+    blue book, and a black book ...
+  example_title: Logic puzzles
+- text: >-
+    The two men running to become New York City's next mayor will face off in
+    their first debate Wednesday night ...
+  example_title: Reading comprehension
 ---
 
 
@@ -32,35 +39,34 @@ widget:
 
 ### Model Description
 
-Using **shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat** as base model, and finetune the dataset as mentioned.
+Using **shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat** as base model, and finetune the dataset as mentioned. Makes the model uncensored.
 
-## Training Procedure
-[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1K9stY8LMVcySG0jDMYZdWQCFPfoDFBL-?usp=sharing) 
+## Training Code
+  [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1K9stY8LMVcySG0jDMYZdWQCFPfoDFBL-?usp=sharing) 
 
 ## Training Procedure Raw Files
 
-ALL the procedure are training on:
-**[[Vast.ai](https://vast.ai/logo.svg)](https://cloud.vast.ai/?ref_id=138637)**
+  ALL the procedure are training on **[Vast.ai](https://cloud.vast.ai/?ref_id=138637)**
+
+
+**Hardware in Vast.ai**: 
 
-**Hardware**: 
   **GPU**: 1x A100 SXM4 80GB
+  
   **CPU**: AMD EPYC 7513 32-Core Processor
+  
   **RAM**: 129 GB
+  
   **Docker Image**: pytorch/pytorch:2.2.0-cuda12.1-cudnn8-devel
-  **Environment**
-  ```python
-    {
-    "DATA_DIRECTORY": "/workspace/",
-    "JUPYTER_DIR": "/"
-    }
-  ```
+  
   **[ipynb file](https://huggingface.co/stephenlzc/dolphin-llama3-zh-cn-uncensored/blob/main/config.json)**
 
+
 ### Training Data
 **Base Model**
-[shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat](https://huggingface.co/shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat)  
+  [shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat](https://huggingface.co/shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat)  
 
 **Dataset**
-- [Minami-su/toxic-sft-zh](https://huggingface.co/datasets/Minami-su/toxic-sft-zh)
-- [llm-wizard/alpaca-gpt4-data-zh](https://huggingface.co/datasets/llm-wizard/alpaca-gpt4-data-zh)
-- [stephenlzc/stf-alpaca](https://huggingface.co/datasets/stephenlzc/stf-alpaca)
+  - [Minami-su/toxic-sft-zh](https://huggingface.co/datasets/Minami-su/toxic-sft-zh)
+  - [llm-wizard/alpaca-gpt4-data-zh](https://huggingface.co/datasets/llm-wizard/alpaca-gpt4-data-zh)
+  - [stephenlzc/stf-alpaca](https://huggingface.co/datasets/stephenlzc/stf-alpaca)