Update README.md

README.md

@@ -34,100 +34,61 @@ language:
 ---
 
 
-## Recommended Prompt Format
 
-```
-### Instruction:
-<instruction>
-
-### Response:
-```
-
-## Recommended Inference Parameters
-
-```yml
-repetition_penalty: 1.15
-do_sample: true
-temperature: 0.5
-top_p: 0.5
-```
 
 
 
 
 
 # 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 model created to act as helpful virtual assistant while maintaing the memory efficiency.
+# Credits
+- **Base Model:** ahxt/llama2_xs_460M_experimental
+- **Dataset used:** timdettmers/openassistant-guanaco
+ - **License:** llama2
 
-Introduction- InstructWise is a model created to act as helpful virtual assistant while maintaing the memory efficiency, this model was fine-tuned on 
 ## Features
-
-- **Creative Content Generation:** NeXGen excels at generating creative writing, including stories, poetry, and fictional narratives.
-- **Contextual Awareness:** The model understands context, ensuring coherent and contextually appropriate responses.
-- **User-Friendly Interface:** NeXGen offers an intuitive and user-friendly interface for seamless integration into various applications.
-- **Versatility:** From content creation to educational support, NeXGen adapts to different writing styles and applications.
-- **Advanced Architecture:** Built on the latest advancements in natural language processing, NeXGen offers high-quality text generation.
+- **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.
 
 ## Uses
 
-NeXGen finds application in various domains, including:
+InstructWise finds application in various domains, including:
 
-- **Content Creation:** Generate marketing copy, stories, and product descriptions.
 - **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.
-- **Social Media Content:** Generate engaging captions for social media posts.
 - **Personal Assistant Applications:** Assist users in drafting emails and messages.
+and many more.
 
 ## Direct Use Cases
 
 NeXGen can be directly employed for:
 
-- **Automated Email Drafting:** Quickly compose emails with NeXGen's assistance.
-- **Blog Post Generation:** Generate sections or entire articles based on a given topic.
-- **Code Commenting:** Improve code documentation with clear and concise comments.
-- **Storyline Creation for Games:** Create dynamic and engaging storylines for video games.
-- **Learning Material Generation:** Develop study guides and educational content.
-- **Personal Journaling Assistance:** Receive prompts and suggestions for journaling.
-
-## Getting Started
-
-To download NeXGen use this code:
-```python
-from transformers import AutoTokenizer, AutoModelForCausalLM
-
-# Specify the model name from Hugging Face Model Hub
-model_name = "CrabfishAI/NeXGen-small"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
-
-def generate_text(prompt, max_length=100, num_beams=5, no_repeat_ngram_size=2, top_k=50, top_p=0.95, temperature=0.7):
-    input_ids = tokenizer.encode(prompt, return_tensors="pt")
-
-    # Ensure attention_mask is provided
-    attention_mask = input_ids.ne(tokenizer.pad_token_id).float()
-
-    # Generate output text
-    output = model.generate(
-        input_ids,
-        max_length=max_length,
-        num_beams=num_beams,
-        no_repeat_ngram_size=no_repeat_ngram_size,
-        top_k=top_k,
-        top_p=top_p,
-        temperature=temperature,
-        attention_mask=attention_mask  # Pass attention_mask to the generation method
-    )
-
-    decoded_output = tokenizer.decode(output[0], skip_special_tokens=True)
-    return decoded_output
-
-# Example usage:
-prompt = "Your prompt here"
-generated_text = generate_text(prompt, max_length=200)
-
-print("Generated Text:")
-print(generated_text)
-```
+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
 
@@ -137,7 +98,7 @@ print(generated_text)
 
 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.
 
-4. **Ambiguous Prompts**: The quality of generated text is highly dependent on the prompt provided. Ambiguous or unclear prompts may result in less coherent or relevant outputs.
+
 
 ## Disclaimer
 
@@ -146,3 +107,21 @@ print(generated_text)
 - **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:
+
+```
+### Instruction:
+<instruction>
+
+### Response:
+```
+
+## Recommended Inference Parameters:
+
+```yml
+repetition_penalty: 1.15
+do_sample: true
+temperature: 0.5
+top_p: 0.5
+```