Update README.md

README.md

@@ -1,61 +1,53 @@
 ---
 license: gemma
 ---
-# 🚀 Nidum Gemma-3-4B IT Uncensored
+# 🚀 Nidum Gemma-3-27B Instruct Uncensored
 
-Welcome to Nidum's Gemma-3-4B IT Uncensored, your gateway to an open and unrestricted AI experience. This powerful model enables users to explore and innovate without boundaries.
+Welcome to Nidum's Gemma-3-27B Instruct Uncensored, a powerful and versatile model optimized for unrestricted interactions. Designed for creators, researchers, and AI enthusiasts seeking innovative and boundary-pushing capabilities.
 
-## ✨ Why Choose Nidum Gemma-3-4B IT Uncensored?
+## ✨ Why Nidum Gemma-3-27B Instruct Uncensored?
 
-- **Unrestricted AI Interaction**: Freedom to discuss, explore, and innovate without content limitations.
-- **Efficient and Versatile**: Optimized performance suitable for various hardware configurations.
-- **Diverse Applications**: Perfect for creative projects, conversational AI, educational tools, and entertainment.
+- **Uncensored Interaction**: Generate content freely without artificial restrictions.
+- **High Intelligence**: Exceptional reasoning and comprehensive conversational capabilities.
+- **Versatile Applications**: Perfect for creative writing, educational interactions, research projects, virtual assistance, and more.
+- **Open and Innovative**: Tailored for users who appreciate limitless creativity.
 
-## 📥 Available Quantized Versions (GGUF)
+## 🚀 Available GGUF Quantized Models
 
-| Quantization | Description                               | Bits per Weight | Download |
-|--------------|-------------------------------------------|-----------------|---------------|
-| **Q8_0**     | Best accuracy and performance               | 8-bit          | [model-Q8_0.gguf](https://huggingface.co/nidum/Nidum-Gemma-3-4B-IT-Uncensored-GGUF/resolve/main/model-Q8_0.gguf) |
-| **Q6_K**     | Balance between speed and quality | 6-bit | [model-Q6_K.gguf](https://huggingface.co/nidum/Nidum-Gemma-3-4B-IT-Uncensored-GGUF/resolve/main/model-Q6_K.gguf) |
-| **Q5_K_M**   | Good accuracy with lower memory usage | 5-bit | [model-Q5_K_M.gguf](https://huggingface.co/nidum/Nidum-Gemma-3-4B-IT-Uncensored-GGUF/resolve/main/model-Q5_K_M.gguf) |
-| **Q3_K_M**   | Smaller footprint, good for limited resources | 3-bit | [model-Q3_K_M.gguf](https://huggingface.co/nidum/Nidum-Gemma-3-4B-IT-Uncensored-GGUF/resolve/main/model-Q3_K_M.gguf) |
-| **TQ2_0**    | Very fast inference, minimal memory usage | 2-bit | [model-TQ2_0.gguf](https://huggingface.co/nidum/Nidum-Gemma-3-4B-IT-Uncensored-GGUF/resolve/main/model-TQ2_0.gguf) |
-| **TQ1_0**    | Minimal memory usage, fastest inference | 2-bit | [model-TQ1_0.gguf](https://huggingface.co/nidum/Nidum-Gemma-3-4B-IT-Uncensored-GGUF/resolve/main/model-TQ1_0.gguf) |
+| Quantization | Bits per Weight | Ideal For | Link |
+|--------------|-----------------|-----------|------|
+| **Q8_0** | 8-bit | Best accuracy and performance | [model-Q8_0.gguf](https://huggingface.co/nidum/nidum-Gemma-3-27B-Instruct-Uncensored-GGUF/blob/main/model-Q8_0.gguf) |
+| **Q6_K** | 6-bit | Strong accuracy and fast inference | [model-Q6_K.gguf](https://huggingface.co/nidum/nidum-Gemma-3-27B-Instruct-Uncensored-GGUF/resolve/main/model-Q6_K.gguf) |
+| **Q5_K_M** | 5-bit | Balance between accuracy and speed | [model-Q5_K_M.gguf](https://huggingface.co/nidum/nidum-Gemma-3-27B-Instruct-Uncensored-GGUF/resolve/main/model-Q5_K_M.gguf) |
+| **Q3_K_M** | 3-bit | Low memory usage, good performance | [model-Q3_K_M.gguf](https://huggingface.co/nidum/nidum-Gemma-3-27B-Instruct-Uncensored-GGUF/resolve/main/model-Q3_K_M.gguf) |
+| **TQ2_0** | 2-bit (Tiny) | Maximum speed and minimal resources | [model-TQ2_0.gguf](https://huggingface.co/nidum/nidum-Gemma-3-27B-Instruct-Uncensored-GGUF/resolve/main/model-TQ2_0.gguf) |
+| **TQ1_0** | 1-bit (Tiny) | Minimal footprint and fastest inference | [model-TQ1_0.gguf](https://huggingface.co/nidum/nidum-Gemma-3-27B-Instruct-Uncensored-GGUF/resolve/main/model-TQ1_0.gguf) |
 
----
-
-## 🚀 Recommended Applications
-
-- **Creative Writing & Arts**: Generate stories, scripts, poetry, and explore creative ideas.
-- **Virtual Assistants**: Provide natural and unrestricted conversational experiences.
-- **Educational Resources**: Facilitate engaging, interactive learning environments.
-- **Entertainment & Gaming**: Create immersive narratives and interactive gameplay experiences.
+## 🎯 Recommended Quantization
+- **Best accuracy**: Use `Q8_0` or `Q6_K`.
+- **Balanced performance**: Use `Q5_K_M`.
+- **Small footprint (mobile/edge)**: Choose `Q3_K_M`, `TQ2_0`, or `TQ1_0`.
 
 ---
 
-## 🎉 Example Usage
+## 🚀 Example Usage (Original Model)
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
-model_name = "nidum/nidum-gemma-3-4b-it-uncensored"
+model_name = "nidum/nidum-Gemma-3-27B-Instruct-Uncensored"
 
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16)
-
-prompt = "Tell me an imaginative story about a hidden city."
-input_ids = tokenizer(prompt, return_tensors="pt").input_ids
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
-generated_ids = model.generate(input_ids, max_length=200)
-output = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
-
-print(output)
+prompt = "Tell me a futuristic story about space travel."
+inputs = tokenizer(prompt, return_tensors="pt")
+output = model.generate(**inputs, max_length=200)
+print(tokenizer.decode(output[0], skip_special_tokens=True))
 ```
 
----
-
-## 🌟 Unlock Limitless Creativity
+## 🚀 Your AI, Your Way
 
-Experience the freedom to innovate and explore without boundaries using **Nidum Gemma-3-4B IT Uncensored**.
+Unlock your creativity and innovation potential with **Nidum Gemma-3-27B Instruct Uncensored**. Experience the freedom to create, explore, and innovate without limits.