Novaeus-Promptist-7B-Instruct Uploaded Model Files
The Novaeus-Promptist-7B-Instruct is a fine-tuned large language model derived from the Qwen2.5-7B-Instruct base model. It is optimized for prompt enhancement, text generation, and instruction-following tasks, providing high-quality outputs tailored to various applications.
| File Name [ Uploaded Files ] | Size | Description | Upload Status |
|---|---|---|---|
.gitattributes | 1.57 kB | Git attributes configuration for LFS. | Uploaded |
README.md | 400 Bytes | Documentation about the model. | Updated |
added_tokens.json | 657 Bytes | Custom tokens for tokenizer. | Uploaded |
config.json | 860 Bytes | Configuration for the model. | Uploaded |
generation_config.json | 281 Bytes | Configuration for text generation. | Uploaded |
merges.txt | 1.82 MB | Byte-pair encoding (BPE) merge rules. | Uploaded |
pytorch_model-00001-of-00004.bin | 4.88 GB | Model weights (split part 1). | Uploaded (LFS) |
pytorch_model-00002-of-00004.bin | 4.93 GB | Model weights (split part 2). | Uploaded (LFS) |
pytorch_model-00003-of-00004.bin | 4.33 GB | Model weights (split part 3). | Uploaded (LFS) |
pytorch_model-00004-of-00004.bin | 1.09 GB | Model weights (split part 4). | Uploaded (LFS) |
pytorch_model.bin.index.json | 28.1 kB | Index file for model weights. | Uploaded |
special_tokens_map.json | 644 Bytes | Map of special tokens for tokenizer. | Uploaded |
tokenizer.json | 11.4 MB | Tokenizer data in JSON format. | Uploaded (LFS) |
tokenizer_config.json | 7.73 kB | Tokenizer configuration file. | Uploaded |
vocab.json | 2.78 MB | Vocabulary for tokenizer. | Uploaded |
Key Features:
-
Prompt Refinement:
Designed to enhance input prompts by rephrasing, clarifying, and optimizing for more precise outcomes. -
Instruction Following:
Accurately follows complex user instructions for various generation tasks, including creative writing, summarization, and question answering. -
Customization and Fine-Tuning:
Incorporates datasets specifically curated for prompt optimization, enabling seamless adaptation to specific user needs.
Training Details:
- Base Model: Qwen2.5-7B-Instruct
- Datasets Used for Fine-Tuning:
- gokaygokay/prompt-enhancer-dataset: Focuses on prompt engineering with 17.9k samples.
- gokaygokay/prompt-enhancement-75k: Encompasses a wider array of prompt styles with 73.2k samples.
- prithivMLmods/Prompt-Enhancement-Mini: A compact dataset (1.16k samples) for iterative refinement.
Capabilities:
-
Prompt Optimization:
Automatically refines and enhances user-input prompts for better generation results. -
Instruction-Based Text Generation:
Supports diverse tasks, including:- Creative writing (stories, poems, scripts).
- Summaries and paraphrasing.
- Custom Q&A systems.
-
Efficient Fine-Tuning:
Adaptable to additional fine-tuning tasks by leveraging the model's existing high-quality instruction-following capabilities.
Usage Instructions:
-
Setup:
- Ensure all necessary model files, including shards, tokenizer configurations, and index files, are downloaded and placed in the correct directory.
-
Load Model:
Use PyTorch or Hugging Face Transformers to load the model and tokenizer. Ensurepytorch_model.bin.index.jsonis correctly set for efficient shard-based loading. -
Customize Generation:
Adjust parameters ingeneration_config.jsonto control aspects such as temperature, top-p sampling, and maximum sequence length.