Downloads · 30 days
25
2% of all-time downloads
Llama-3.2-3B-Promptist-Mini
prithivMLmods/Llama-3.2-3B-Promptist-Mini
Llama-3.2-3B-Promptist-Mini is a text generation model from prithivMLmods. Use it when you need the model to write or continue text. The card lists the license as creativeml-openrail-m.
The Llama-3.2-3B-Promptist-Mini is a fine-tuned version of the Llama-3.2-3B-Instruct model, specifically optimized for prompt engineering and enhancement tasks. It is ideal for generating and enhancing various types o…
All-time downloads
1.3K
Public
Repo size
12.9 GB
Likes
4
Public
Repo makeup
Click a slice to open those files.
.safetensors6.4 GB · 100%
At a glance
- Task
- Text Generation
- License
- creativeml-openrail-m
- Model type
- llama
- Access
- Public
- Created
- Dec 4, 2024
- Updated
- Jan 6, 2025
- SHA
- ef2005e8
Try a prompt
Base models
Model card
From the Hugging Face model README
Llama-3.2-3B-Promptist-Mini Model Files
The Llama-3.2-3B-Promptist-Mini is a fine-tuned version of the Llama-3.2-3B-Instruct model, specifically optimized for prompt engineering and enhancement tasks. It is ideal for generating and enhancing various types of text prompts, offering high performance in creative and instructional applications. The model leverages a smaller, more efficient architecture suited for fine-tuning and prompt-based use cases.
| File Name | Size | Description | Upload Status |
|---|---|---|---|
.gitattributes | 1.52 kB | Git attributes configuration file | Uploaded |
README.md | 287 Bytes | Updated README file | Updated |
config.json | 940 Bytes | Model configuration settings | Uploaded |
generation_config.json | 162 Bytes | Generation-specific configurations | Uploaded |
merges.txt | 515 kB | Merging information for tokenization | Uploaded |
pytorch_model.bin | 3.42 GB | Full model weights (PyTorch format) | Uploaded (LFS) |
special_tokens_map.json | 572 Bytes | Mapping for special tokens used by the model | Uploaded |
tokenizer.json | 3.77 MB | Tokenizer configuration and vocabulary | Uploaded |
tokenizer_config.json | 3.95 kB | Tokenizer configuration for loading and usage | Uploaded |
vocab.json | 801 kB | Vocabulary for the tokenizer | Uploaded |
Key Features:
-
Prompt Engineering and Enhancement:
This model is fine-tuned to generate and improve prompts for various applications, such as question generation, creative writing, and instruction-following tasks. -
Text Generation:
It excels in generating coherent and contextually relevant text based on the given prompts. The model can be used for a wide range of text-based applications, including content creation and automated text generation. -
Custom Tokenizer:
Includes a tokenizer optimized for handling specialized tokens related to prompt-based tasks, ensuring the model performs well in generating creative and logical text.
Training Details:
- Base Model: Llama-3.2-3B-Instruct
- Dataset: Trained on Prompt-Enhancement-Mini, a dataset specifically designed to enhance prompt generation, with examples tailored to creative and instructional contexts.
Capabilities:
-
Prompt Generation and Enhancement:
The model can generate and enhance prompts for various tasks, including machine learning, creative writing, and instructional content. -
Text Generation:
It excels at generating coherent, structured, and contextually appropriate text from user inputs, making it suitable for a wide variety of text-based applications.
Usage Instructions:
- Model Setup: Download all model files and ensure the PyTorch model weights and tokenizer configurations are included.
- Inference: Load the model in a Python environment using frameworks like PyTorch or Hugging Face's Transformers.
- Customization: Configure the model with the
config.jsonandgeneration_config.jsonfiles for optimal performance during inference.
- Task
- Text Generation
- Type
- llama
- License
- creativeml-openrail-m
- Languages
- en
- Created
- Dec 4, 2024
- Updated
- Jan 6, 2025