Downloads · 30 days
165
5% of all-time downloads
YugoGPT-7B-Instruct-GGUF
W4D/YugoGPT-7B-Instruct-GGUF
YugoGPT-7B-Instruct-GGUF is a machine learning model from W4D. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
YugoGPT Instruct is a fine-tuned version of the YugoGPT base model designed specifically for translation tasks involving Serbian, Croatian, and Bosnian languages. Unlike the base model, this instruct model is optimize…
All-time downloads
3K
Public
Repo size
57.3 GB
Likes
4
Public
Repo makeup
Click a slice to open those files.
.gguf57.3 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jan 9, 2025
- Updated
- Jan 10, 2025
- SHA
- 2967fcb3
Base models
Datasets
Model card
From the Hugging Face model README
YugoGPT Instruct
YugoGPT Instruct is a fine-tuned version of the YugoGPT base model designed specifically for translation tasks involving Serbian, Croatian, and Bosnian languages. Unlike the base model, this instruct model is optimized for following user instructions, offering improved performance in instruction-based interactions.
Overview
YugoGPT Instruct builds upon the powerful capabilities of the YugoGPT base model, fine-tuning it to enhance its usability in structured and directive tasks. This model is ideal for translation workflows where accuracy and context preservation are critical.
Features
- Specialized for BCS Languages: Tailored for Serbian, Croatian, and Bosnian language translations.
- Instruction Following: Fine-tuned to better adhere to user-provided instructions.
- Flexible Deployment: Compatible with various quantization formats for different computational environments.
Quantization Formats
A variety of quantization formats are available to suit diverse performance and resource requirements. Below is the table of quantization options:
| Filename | Quant Type | Description |
|---|---|---|
YugoGPT-7B-Instruct-F16 | F16 | Full F16 precision, maximum quality. |
YugoGPT-7B-Instruct-Q8_0 | Q8_0 | Extremely high quality. |
YugoGPT-7B-Instruct-Q6_K | Q6_K | Very high quality, near perfect, recommended. |
YugoGPT-7B-Instruct-Q5_K_M | Q5_K_M | High quality, recommended. |
YugoGPT-7B-Instruct-Q5_K_S | Q5_K_S | High quality with optimal trade-offs. |
YugoGPT-7B-Instruct-Q4_K_M | Q4_K_M | Good quality, optimized for speed. |
YugoGPT-7B-Instruct-Q4_K_S | Q4_K_S | Slightly lower quality with more savings. |
YugoGPT-7B-Instruct-Q3_K_L | Q3_K_L | Lower quality, good for low RAM systems. |
YugoGPT-7B-Instruct-Q3_K_M | Q3_K_M | Low quality, optimized for size. |
YugoGPT-7B-Instruct-Q3_K_S | Q3_K_S | Low quality, not recommended. |
Usage
For usage with Ollama, you can initialize the model using the provided modelfile in the repository. Follow Ollama’s setup instructions to get started.
Replace {__FILE_LOCATION__} with the file name of the quant you want to use when creating the model using Ollama CLI.
Licensing
This model is released under the Apache 2.0 License, the same as the YugoGPT base repository.
Credits
- Base Model: YugoGPT by Aleksa Gordić
- Fine-Tuning Framework: Unsloth
- License
- apache-2.0
- Languages
- en, sr, bs, hr
- Created
- Jan 9, 2025
- Updated
- Jan 10, 2025