Update README.md

README.md

@@ -13,55 +13,48 @@ tags:
 - text-generation-inference
 ---
 
-
-
 <p align="center">
 <img width="700px" alt="DeepSeek Coder" src="https://cdn-uploads.huggingface.co/production/uploads/64b566ab04fa6584c03b5247/5COagfF6EwrV4utZJ-ClI.png">
 </p>
 <hr>
 
+# CodeNinja: Your Advanced Coding Assistant
+
+## Overview
 
-## 1. Introduction of CodeNinja
+CodeNinja is an enhanced version of the renowned model [openchat/openchat-3.5-1210](https://huggingface.co/openchat/openchat-3.5-1210). It represents a breakthrough in coding assistance, having been fine-tuned through Supervised Fine Tuning on two expansive datasets, encompassing over 400,000 coding instructions. Designed to be an indispensable tool for coders, CodeNinja aims to integrate seamlessly into your daily coding routine.
 
-CodeNinja is a fine tuned version of the excellent model [openchat/openchat-3.5-1210](https://huggingface.co/openchat/openchat-3.5-1210). It is a 7B model that was fine tuned using Supervised Fine Tuning in 2 instructions datasets containing in total more than 400 000 code instructions.
+Discover the quantized versions at: [beowolx/CodeNinja-1.0-OpenChat-7B-GGUF](https://huggingface.co/beowolx/CodeNinja-1.0-OpenChat-7B-GGUF).
 
-The model is quite good for coding tasks and it's goal is to be a coding assistant that you can use daily.
+### Key Features
 
-The quantized versions can be found here: [beowolx/CodeNinja-1.0-OpenChat-7B-GGUF](https://huggingface.co/beowolx/CodeNinja-1.0-OpenChat-7B-GGUF).
+- **Expansive Training Database**: CodeNinja has been refined with datasets from [glaiveai/glaive-code-assistant-v2](https://huggingface.co/datasets/glaiveai/glaive-code-assistant-v2) and [TokenBender/code_instructions_122k_alpaca_style](https://huggingface.co/datasets/TokenBender/code_instructions_122k_alpaca_style), incorporating around 400,000 coding instructions across various languages including Python, C, C++, Rust, Java, JavaScript, and more.
 
-The model performs very good in a serie of different tasks.
+- **Flexibility and Scalability**: Available in a 7B model size, CodeNinja is adaptable for local runtime environments.
 
-- **Massive Training Data**: Fine-tuned using the datasets [glaiveai/glaive-code-assistant-v2](https://huggingface.co/datasets/glaiveai/glaive-code-assistant-v2) and [TokenBender/code_instructions_122k_alpaca_style](https://huggingface.co/datasets/TokenBender/code_instructions_122k_alpaca_style) it contains around 400 000 code instructions in different programming languages such as Python, C, C++, Rust, Java, JavaScript and etc.
-  
-- **Highly Flexible & Scalable**: Offered in model sizes of 7B, enabling users to run it locally.
-  
-- **Superior Model Performance**: State-of-the-art performance among publicly available code models on HumanEval.
-  
-- **Advanced Code Completion Capabilities**: A context window size of 8192 supporting project-level code completion.
+- **Exceptional Performance**: Achieves top-tier results among publicly accessible coding models, particularly notable on benchmarks like HumanEval.
 
-## 2. Prompt Format
-CodeNinja uses the same prompt format than OpenChat 3.5 so you will need to use it to get good results.
+- **Advanced Code Completion**: With a substantial context window size of 8192, it supports comprehensive project-level code completion.
 
-The prompt format looks like this:
+## Prompt Format
+
+CodeNinja maintains the same prompt structure as OpenChat 3.5. Effective utilization requires adherence to this format:
 
 ```
 GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant: Hi<|end_of_turn|>GPT4 Correct User: How are you today?<|end_of_turn|>GPT4 Correct Assistant:
 ```
-🚨 Notice: Remember to set `<|end_of_turn|>` as end of generation token.
 
-**You must use this prompt format to get good results**
+🚨 Important: Ensure the use of `<|end_of_turn|>` as the end-of-generation token.
 
-## 3. How to Use
+**Adhering to this format is crucial for optimal results.**
 
-#### Using LM Studio
-The easiest way to start using the model is to download one of the [quantized](https://huggingface.co/beowolx/CodeNinja-1.0-OpenChat-7B-GGUF) versions
-using [LM Studio](https://lmstudio.ai/).
+## Usage Instructions
 
-You then need to make sure that you are using the "OpenChat" preset that contain the prompt format mentioned above already set.
+### Using LM Studio
 
-If you want, you can get the preset from this [gist](https://gist.github.com/beowolx/b219466681c02ff67baf8f313a3ad817).
+The simplest way to engage with CodeNinja is via the [quantized versions](https://huggingface.co/beowolx/CodeNinja-1.0-OpenChat-7B-GGUF) on [LM Studio](https://lmstudio.ai/). Ensure you select the "OpenChat" preset, which incorporates the necessary prompt format. The preset is also available in this [gist](https://gist.github.com/beowolx/b219466681c02ff67baf8f313a3ad817).
 
-#### Using the transformers library
+### Using the Transformers Library
 
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
@@ -70,37 +63,35 @@ import torch
 # Initialize the model
 model_path = "beowolx/CodeNinja-1.0-OpenChat-7B"
 model = AutoModelForCausalLM.from_pretrained(model_path, device_map="auto")
-# Import openchat tokenizer
+# Load the OpenChat tokenizer
 tokenizer = AutoTokenizer.from_pretrained("openchat/openchat-3.5-1210", use_fast=True)
 
 def generate_one_completion(prompt: str):
     messages = [
         {"role": "user", "content": prompt},
-        {"role": "assistant", "content": ""}  # Placeholder for the model's response
+        {"role": "assistant", "content": ""}  # Model response placeholder
     ]
 
-    # Apply the chat template to get the list of token IDs
+    # Generate token IDs using the chat template
     input_ids = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
 
-    # Generate completion
+    # Produce completion
     generate_ids = model.generate(
-        torch.tensor([input_ids]).to("cuda"),  # Convert list to tensor and send to GPU
+        torch.tensor([input_ids]).to("cuda"),
         max_length=256,
         pad_token_id=tokenizer.pad_token_id,
         eos_token_id=tokenizer.eos_token_id
     )
 
-    # Decode and clean up the completion
+    # Process the completion
     completion = tokenizer.decode(generate_ids[0], skip_special_tokens=True)
     completion = completion.split("\n\n\n")[0].strip()
 
     return completion
 ```
 
-## 4. License
-This code repository is licensed under the MIT License. The use of CodeNinja model is subject to the Model License.
-
-
-## 5. Contact
+## License
+CodeNinja is licensed under the MIT License, with model usage subject to the Model License.
 
-If you have any questions, please raise an issue here.
+## Contact
+For queries or support, please open an issue in the repository.