Text Generation
Transformers
Safetensors
English
llama
codepy
ollama
llama-cpp
trl
deep-think
coder
conversational
text-generation-inference
Instructions to use prithivMLmods/Codepy-Deepthink-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use prithivMLmods/Codepy-Deepthink-3B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="prithivMLmods/Codepy-Deepthink-3B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("prithivMLmods/Codepy-Deepthink-3B") model = AutoModelForCausalLM.from_pretrained("prithivMLmods/Codepy-Deepthink-3B", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use prithivMLmods/Codepy-Deepthink-3B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "prithivMLmods/Codepy-Deepthink-3B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "prithivMLmods/Codepy-Deepthink-3B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/prithivMLmods/Codepy-Deepthink-3B
- SGLang
How to use prithivMLmods/Codepy-Deepthink-3B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "prithivMLmods/Codepy-Deepthink-3B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "prithivMLmods/Codepy-Deepthink-3B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "prithivMLmods/Codepy-Deepthink-3B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "prithivMLmods/Codepy-Deepthink-3B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use prithivMLmods/Codepy-Deepthink-3B with Docker Model Runner:
docker model run hf.co/prithivMLmods/Codepy-Deepthink-3B
| license: creativeml-openrail-m | |
| pipeline_tag: text-generation | |
| library_name: transformers | |
| language: | |
| - en | |
| base_model: | |
| - meta-llama/Llama-3.2-3B-Instruct | |
| tags: | |
| - codepy | |
| - safetensors | |
| - ollama | |
| - llama-cpp | |
| - trl | |
| - deep-think | |
| - coder | |
| # **Codepy 3B Deep Think Model File** | |
| The **Codepy 3B Deep Think Model** is a fine-tuned version of the **meta-llama/Llama-3.2-3B-Instruct** base model, designed for text generation tasks that require deep reasoning, logical structuring, and problem-solving. This model leverages its optimized architecture to provide accurate and contextually relevant outputs for complex queries, making it ideal for applications in education, programming, and creative writing. | |
| With its robust natural language processing capabilities, **Codepy 3B Deep Think** excels in generating step-by-step solutions, creative content, and logical analyses. Its architecture integrates advanced understanding of both structured and unstructured data, ensuring precise text generation aligned with user inputs. | |
| | **Model Content** | **Size** | **Description** | **Upload Status** | | |
| |-----------------------------------|----------------|------------------------------------------------|-------------------| | |
| | `.gitattributes` | 1.57 kB | Git LFS configuration for large files. | Uploaded | | |
| | `README.md` | 221 Bytes | Basic repository information. | Updated | | |
| | `config.json` | 994 Bytes | Model configuration with architectural details. | Uploaded | | |
| | `generation_config.json` | 248 Bytes | Default generation parameters. | Uploaded | | |
| | `pytorch_model-00001-of-00002.bin`| 4.97 GB | Sharded PyTorch model weights (part 1 of 2). | Uploaded (LFS) | | |
| | `pytorch_model-00002-of-00002.bin`| 1.46 GB | Sharded PyTorch model weights (part 2 of 2). | Uploaded (LFS) | | |
| | `pytorch_model.bin.index.json` | 21.2 kB | Index file mapping model shards. | Uploaded | | |
| | `special_tokens_map.json` | 477 Bytes | Maps special tokens to their respective IDs. | Uploaded | | |
| | `tokenizer.json` | 17.2 MB | Full tokenizer vocabulary and merges. | Uploaded (LFS) | | |
| | `tokenizer_config.json` | 57.5 kB | Tokenizer configuration details. | Uploaded | | |
| | Run with LM Studio | Details | | |
| |--------------------------|-----------------------------------------------------------------------------------------------| | |
| | *Run with LM Studio* | https://lmstudio.ai/ | | |
| | *Demo on LM Studio* | https://drive.google.com/file/d/1CHdfjYrwMnk9ACvS40Abfy3xNXnCubKG/view?usp=sharing | | |
| | *Codepy-Deepthink-3B-GGUF* | https://huggingface.co/prithivMLmods/Codepy-Deepthink-3B-GGUF | | |
| --- | |
| # **<span style="color:red;">Sample Deepthink Inference</span>** | |
| >>> Develop a Python program to generate random passwords that consist of 8 characters. Not applicable | |
| ```markdown | |
| # Random Password Generator | |
| This Python program generates a random password of a specified length (default: 8 characters) that includes a mix of lowercase letters, uppercase letters, digits, and spaces. The program ensures the generated password meets basic security requirements while maintaining simplicity. | |
| ## Features | |
| - Generates alphanumeric passwords with optional spaces. | |
| - Ensures at least one lowercase letter, one uppercase letter, one digit, and one space in the password. | |
| - Shuffles the characters to randomize the order. | |
| - Includes error handling for invalid input lengths. | |
| ## Requirements | |
| - Python 3.x | |
| ## Usage | |
| 1. Clone or download this repository. | |
| 2. Run the script using Python: | |
| ```bash | |
| python password_generator.py | |
| ``` | |
| 3. The script will generate and print an 8-character random password to the console. | |
| ## Code | |
| ```python | |
| import random | |
| def generate_password(length): | |
| """ | |
| Generates a random alphanumeric password of the specified length. | |
| Ensures that at least one lowercase letter, one uppercase letter, | |
| one digit, and one space are included in the password. | |
| Args: | |
| length: The number of characters in the password. | |
| Returns: | |
| A string representing the generated password or None if the input is invalid. | |
| """ | |
| # Define a set of alphanumeric characters with spaces | |
| characters = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789 ' | |
| # Validate the length | |
| if length < 1: | |
| return None | |
| # Handle invalid length | |
| if length > len(characters): | |
| print("Invalid password length. It should be less than or equal to", len(characters)) | |
| return None | |
| # Ensure at least one character from each required group | |
| required_characters = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789 ' | |
| if length > 1: | |
| password_length_without_requirements = length - 4 | |
| random_string = ''.join(random.choice(required_characters) for _ in range(password_length_without_requirements)) | |
| # Fill the rest of the password with random characters | |
| remaining_chars_needed = length - len(random_string) | |
| all_possible_chars = list(characters) | |
| if length > 1: | |
| random_character = random.choice('abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789 ') | |
| else: | |
| random_character = random.choice('abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789 ') | |
| password = random_string + random_character * remaining_chars_needed | |
| # Shuffle the password to avoid predictable patterns | |
| password_list = list(password) | |
| random.shuffle(password_list) | |
| password = ''.join(password_list) | |
| return password | |
| # Example Usage | |
| password_length = 8 | |
| generated_password = generate_password(password_length) | |
| if generated_password is not None: | |
| print(f"Generated Password: {generated_password}") | |
| else: | |
| print("Failed to generate a password. Please ensure the length is valid (between 1 and", len(characters), ").") | |
| ``` | |
| ## Example Output | |
| ``` | |
| Generated Password: g7x 2PqA | |
| ``` | |
| ## Customization | |
| To customize the password length, modify the `password_length` variable in the script. | |
| ## Security Notes | |
| - This implementation uses Python's `random` module, which is suitable for general-purpose randomness. For cryptographically secure passwords, consider using the `secrets` module. | |
| - The character set includes spaces for additional complexity, but you can modify the `characters` string to include other symbols (e.g., `!@#$%^&*`). | |
| --- | |
| # **Model Architecture** | |
| Llama 3.2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety. | |
| # **Run with Ollama [ Ollama Run ]** | |
| Ollama simplifies running machine learning models. This guide walks you through downloading, installing, and running GGUF models in minutes. | |
| ## Table of Contents | |
| - [Download and Install](#download-and-install) | |
| - [Run GGUF Models](#run-gguf-models) | |
| - [Running the Model](#running-the-model) | |
| - [Sample Usage](#sample-usage) | |
| ## Download and Install | |
| Download Ollama from [https://ollama.com/download](https://ollama.com/download) and install it on your Windows or Mac system. | |
| ## Run GGUF Models | |
| 1. **Create the Model File** | |
| Create a model file, e.g., `metallama`. | |
| 2. **Add the Template Command** | |
| Include a `FROM` line in the file to specify the base model: | |
| ```bash | |
| FROM Llama-3.2-1B.F16.gguf | |
| ``` | |
| 3. **Create and Patch the Model** | |
| Run the following command: | |
| ```bash | |
| ollama create metallama -f ./metallama | |
| ``` | |
| Verify the model with: | |
| ```bash | |
| ollama list | |
| ``` | |
| ## Running the Model | |
| Run your model with: | |
| ```bash | |
| ollama run metallama | |
| ``` | |
| ### Sample Usage | |
| Interact with the model: | |
| ```plaintext | |
| >>> write a mini passage about space x | |
| Space X, the private aerospace company founded by Elon Musk, is revolutionizing the field of space exploration... | |
| ``` | |
| --- | |
| With these steps, you can easily run custom models using Ollama. Adjust as needed for your specific use case. |