Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- meta-llama/Meta-Llama-3-8B
|
| 4 |
+
- ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1
|
| 5 |
+
- ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1
|
| 6 |
+
tags:
|
| 7 |
+
- merge
|
| 8 |
+
- mergekit
|
| 9 |
+
- lazymergekit
|
| 10 |
+
- meta-llama/Meta-Llama-3-8B
|
| 11 |
+
- ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1
|
| 12 |
+
- ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# Turkish-Llama3-8B-Merged GGUF Quantized Models
|
| 16 |
+
|
| 17 |
+
## Technical Details
|
| 18 |
+
- **Quantization Tool:** llama.cpp
|
| 19 |
+
- **Version:** ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
|
| 20 |
+
|
| 21 |
+
## Model Information
|
| 22 |
+
- **Base Model:** [matrixportal/Turkish-Llama3-8B-Merged](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged)
|
| 23 |
+
- **Quantized by:** [matrixportal](https://huggingface.co/matrixportal)
|
| 24 |
+
|
| 25 |
+
## Available Files
|
| 26 |
+
| 🚀 Download | 🔢 Type | 📝 Description |
|
| 27 |
+
|------------|---------|---------------|
|
| 28 |
+
| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.q2_k.gguf) | Q2 K | Tiny size, lowest quality (emergency use only) |
|
| 29 |
+
| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.q3_k_s.gguf) | Q3 K S | Very small, low quality (basic tasks) |
|
| 30 |
+
| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.q3_k_m.gguf) | Q3 K M | Small, acceptable quality |
|
| 31 |
+
| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.q3_k_l.gguf) | Q3 K L | Small, better than Q3_K_M (good for low RAM) |
|
| 32 |
+
| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.q4_0.gguf) | Q4 0 | Standard 4-bit (fast on ARM) |
|
| 33 |
+
| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.q4_k_s.gguf) | Q4 K S | 4-bit optimized (good space savings) |
|
| 34 |
+
| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.q4_k_m.gguf) | Q4 K M | 4-bit balanced (recommended default) |
|
| 35 |
+
| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.q5_0.gguf) | Q5 0 | 5-bit high quality |
|
| 36 |
+
| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.q5_k_s.gguf) | Q5 K S | 5-bit optimized |
|
| 37 |
+
| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.q5_k_m.gguf) | Q5 K M | 5-bit best (recommended HQ option) |
|
| 38 |
+
| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.q6_k.gguf) | Q6 K | 6-bit near-perfect (premium quality) |
|
| 39 |
+
| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.q8_0.gguf) | Q8 0 | 8-bit maximum (overkill for most) |
|
| 40 |
+
| [Download](https://huggingface.co/matrixportal/Turkish-Llama3-8B-Merged-GGUF/resolve/main/turkish-llama3-8b-merged.f16.gguf) | F16 | Full precision (maximum accuracy) |
|
| 41 |
+
|
| 42 |
+
💡 **Q4 K M** provides the best balance for most use cases
|