Update README.md

README.md

@@ -1,70 +1,140 @@
 ---
-license: apache-2.0
 tags:
-  - autotrain
-  - text-generation
+- autotrain
+- text-generation
 base_model: Locutusque/TinyMistral-248M
 datasets:
-  - OpenAssistant/oasst_top1_2023-08-25
+- CrabfishAI/ReasoningQuestions
+- OpenAssistant/oasst_top1_2023-08-25
+- nRuaif/OpenOrca-GPT3.5
 widget:
-  - text: |-
-      <|im_start|>user
-      Write the specs of a game about trolls and warriors in a fantasy world.<|im_end|>
-      <|im_start|>assistant
-      The game is an adventure game that takes place on a planet, where players must explore their unique abilities to survive. Players can use different strategies such as collecting items or trading them for gold or silver coins, but they also need to learn how to deal with obstacles and find new ways to escape.<|im_end|>
-      <|im_start|>user
-      Could you tell me something curious about the Earth?<|im_end|>
-      <|im_start|>assistant
-      The planet is a large, rocky world with an atmosphere of 10 billion years old and a surface area around 25 million miles (36 million kilometers) wide.<|im_end|>
-      <|im_start|>user
-      What are some potential applications for quantum computing?<|im_end|>
-      <|im_start|>assistant
+- text: |-
+    <|im_start|>user
+    Find me a list of some nice places to visit around the world.<|im_end|>
+
+
+
+
+    <|im_start|>assistant
+- text: |-
+    <|im_start|>user
+    Tell me a story about some magical place.<|im_end|>
+
+
+
+
+    <|im_start|>assistant
+
+- text: |-
+    <|im_start|>user
+    Write a python code to print numbers from 1 to 100 in sequence.<|im_end|>
+    
+
+
+
+    <|im_start|>assistant
+- text: |-
+    <|im_start|>user
+    What is biology?<|im_end|>
+
+
+
+
+    <|im_start|>assistant
+- text: >-
+    <|im_start|>user
+    I love taking photos of nature. Can you come up with a 3-day itinerary
+    visiting the most photogenic places in Iceland?<|im_end|>
+
+
+
+
+    <|im_start|>assistant
 inference:
   parameters:
-    max_new_tokens: 64
-    repetition_penalty: 1.18
+    max_new_tokens: 32
+    repetition_penalty: 1.15
+    do_sample: true
+    temperature: 0.5
+    top_p: 0.5
+license: apache-2.0
+language:
+- en
 ---
 
-# Locutusque's TinyMistral-248M trained on OpenAssistant TOP-1 Conversation Threads
 
-- Base model: [Locutusque/TinyMistral-248M](https://huggingface.co/Locutusque/TinyMistral-248M/blob/90b89d18fdf27937dc04ab8a9b543c5af2991c7f/README.md)
-- Dataset: [OpenAssistant/oasst_top1_2023-08-25](https://huggingface.co/datasets/OpenAssistant/oasst_top1_2023-08-25)
+# InstructWise 470M - A virtual assistant.
+Note- we,ll be releasing more versions of InstructWise soon, with the goal of making memory-efficent models while maintaining the performance, Thank you!
+
+Introduction- InstructWise is a series of model created to act as helpful virtual assistant while maintaing the memory efficiency.
+# Credits
+- **Base Model:** Locutusque/TinyMistral-248M
+- **Dataset Used:** (Mentioned earlier)
+ - **License:** Apache License 2.0
+
+## Features
+- **Maintaining performance while being memory efficient:** Ram usage- 7.1GB Vram usage- 0.6GB (approximately)
+- **Act as helpful virtual assistant:** InstructWise serves as a versatile and helpful assistant, offering a range of features that cater to various user needs. Its key strength lies in providing instructive responses to user prompts, offering detailed and insightful information. 
+- **Coding:** Model can perform coding as well.
+- **Assisting capabilities:** can assist with wide rang of taskes.
 
-## Recommended Prompt Format
+## Uses
 
+InstructWise finds application in various domains, including:
+
+- **Assistance in Writing:** Aid authors, bloggers, and students in drafting articles and essays.
+- **Chatbot Development:** Power conversational agents with human-like responses.
+- **Prototyping and Idea Generation:** Facilitate brainstorming sessions for product development.
+- **Personal Assistant Applications:** Assist users in drafting emails and messages.
+and many more.
+
+## Direct Use Cases
+
+InstructWise can be directly employed for:
+
+1. **Educational Support:**
+   - Assist users in learning new topics with detailed explanations and step-by-step instructions.
+
+2. **Content Creation:**
+   - Generate creative content based on prompts, aiding content creators in the writing process.
+
+3. **Code Assistance:**
+   - Provide guidance on coding queries, improve code documentation, and generate code snippets for developers.
+
+4. **Interactive Conversations:**
+   - Enhance chatbots or virtual assistants with informative and helpful responses for users.
+
+5. **Q&A Platforms:**
+   - Power question and answer platforms, offering detailed and insightful answers on various topics.
+
+6. **Technical Writing Support:**
+   - Assist writers and technical communicators with suggestions for clarity and informativeness.
+
+7. **Idea Expansion:**
+   - Facilitate the expansion and development of ideas by providing detailed insights and suggestions.
+
+
+## Limitation
+
+1. **Content Quality**: The model's output may vary in quality, and there's a possibility it might generate content that is nonsensical, irrelevant, or grammatically incorrect.
+
+2. **Bias and Sensitivity**: The model is trained on diverse data, but it may inadvertently exhibit biases or generate content that is sensitive or inappropriate. Exercise caution and review generated text before use.
+
+3. **Inappropriate Language**: The model might generate text that includes offensive language or inappropriate content. Be mindful of this, especially in applications where maintaining a respectful and inclusive tone is essential.
+
+
+
+## Disclaimer
+
+- **Use with Caution**: This model is a tool that should be used with caution. Always review and validate the generated text before incorporating it into any application or publication.
+
+- **Not for Critical Applications**: Avoid using the model for critical applications where accuracy and reliability are paramount. The model is intended for creative and exploratory purposes.
+
+- **Ongoing Improvement**: The model may be updated or fine-tuned for better performance. Stay informed about updates and consider using the latest version for improved results.
+
+## Recommended Prompt Format to use:
 ```
 <|im_start|>user
 {message}<|im_end|>
 <|im_start|>assistant
-```
-
-## How it was trained
-
-```ipython
-%pip install autotrain-advanced
-
-!autotrain setup
-
-!autotrain llm \
-    --train \
-    --trainer "sft" \
-    --model './TinyMistral-248M/' \
-    --model_max_length 4096 \
-    --block-size 1024 \
-    --project-name 'trained-model' \
-    --data-path "OpenAssistant/oasst_top1_2023-08-25" \
-    --train_split "train" \
-    --valid_split "test" \
-    --text-column "text" \
-    --lr 1e-5 \
-    --train_batch_size 2 \
-    --epochs 5 \
-    --evaluation_strategy "steps" \
-    --save-strategy "steps" \
-    --save-total-limit 2 \
-    --warmup-ratio 0.05 \
-    --weight-decay 0.0 \
-    --gradient-accumulation 8 \
-    --logging-steps 10 \
-    --scheduler "constant"
 ```