41 lines
3.3 KiB
Markdown
41 lines
3.3 KiB
Markdown
|
---
|
||
|
|
datasets:
|
||
|
|
- matrixportal/aya-turkish-alpaca
|
||
|
|
- cenfis/alpaca-turkish-combined
|
||
|
|
- merve/turkish_instructions
|
||
|
|
- CohereLabs/aya_collection_language_split
|
||
|
|
language:
|
||
|
|
- tr
|
||
|
|
- en
|
||
|
|
base_model:
|
||
|
|
- meta-llama/Meta-Llama-3-8B-Instruct
|
||
|
|
---
|
||
|
|
|
||
|
|
# Llama3-8B-Instruct-Turkish-Finetuned GGUF Quantized Models
|
||
|
|
|
||
|
|
## Technical Details
|
||
|
|
- **Quantization Tool:** llama.cpp
|
||
|
|
- **Version:** version: 5162 (2016f07b)
|
||
|
|
|
||
|
|
## Model Information
|
||
|
|
- **Base Model:** [matrixportal/Llama3-8B-Instruct-Turkish-Finetuned](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned)
|
||
|
|
- **Quantized by:** [matrixportal](https://huggingface.co/matrixportal)
|
||
|
|
|
||
|
|
## Available Files
|
||
|
|
| 🚀 Download | 🔢 Type | 📝 Description |
|
||
|
|
|------------|---------|---------------|
|
||
|
|
| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.q2_k.gguf) | Q2 K | Tiny size, lowest quality (emergency use only) |
|
||
|
|
| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.q3_k_s.gguf) | Q3 K S | Very small, low quality (basic tasks) |
|
||
|
|
| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.q3_k_m.gguf) | Q3 K M | Small, acceptable quality |
|
||
|
|
| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.q3_k_l.gguf) | Q3 K L | Small, better than Q3_K_M (good for low RAM) |
|
||
|
|
| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.q4_0.gguf) | Q4 0 | Standard 4-bit (fast on ARM) |
|
||
|
|
| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.q4_k_s.gguf) | Q4 K S | 4-bit optimized (good space savings) |
|
||
|
|
| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.q4_k_m.gguf) | Q4 K M | 4-bit balanced (recommended default) |
|
||
|
|
| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.q5_0.gguf) | Q5 0 | 5-bit high quality |
|
||
|
|
| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.q5_k_s.gguf) | Q5 K S | 5-bit optimized |
|
||
|
|
| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.q5_k_m.gguf) | Q5 K M | 5-bit best (recommended HQ option) |
|
||
|
|
| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.q6_k.gguf) | Q6 K | 6-bit near-perfect (premium quality) |
|
||
|
|
| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.q8_0.gguf) | Q8 0 | 8-bit maximum (overkill for most) |
|
||
|
|
| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.f16.gguf) | F16 | Full precision (maximum accuracy) |
|
||
|
|
|
||
|
|
💡 **Q4 K M** provides the best balance for most use cases
|