Update README.md
Browse files
README.md
CHANGED
|
@@ -69,7 +69,27 @@ print(assistant_response)
|
|
| 69 |
```
|
| 70 |
|
| 71 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
|
|
|
|
| 73 |
### Datasets and Fine-Tuning
|
| 74 |
|
| 75 |
The following fine-tuning datasets are leveraged to enhance specific model capabilities:
|
|
|
|
| 69 |
```
|
| 70 |
|
| 71 |
---
|
| 72 |
+
#### Quantized Models Available for Download
|
| 73 |
+
|
| 74 |
+
| **Quantized Model Version** | **Description** |
|
| 75 |
+
|-------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------|
|
| 76 |
+
| [**Nidum-Llama-3.2-3B-Uncensored-F16.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/Nidum-Llama-3.2-3B-Uncensored-F16.gguf) | Full 16-bit floating point precision for maximum accuracy on high-end GPUs. |
|
| 77 |
+
| [**model-Q2_K.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-Q2_K.gguf) | Optimized for minimal memory usage with lower precision, suitable for edge cases.|
|
| 78 |
+
| [**model-Q3_K_L.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-Q3_K_L.gguf) | Balanced precision with enhanced memory efficiency for medium-range devices. |
|
| 79 |
+
| [**model-Q3_K_M.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-Q3_K_M.gguf) | Mid-range quantization for moderate precision and memory usage balance. |
|
| 80 |
+
| [**model-Q3_K_S.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-Q3_K_S.gguf) | Smaller quantization steps, offering moderate precision with reduced memory use.|
|
| 81 |
+
| [**model-Q4_0_4_4.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-Q4_0_4_4.gguf) | Performance-optimized for low memory, ideal for lightweight deployment. |
|
| 82 |
+
| [**model-Q4_0_4_8.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-Q4_0_4_8.gguf) | Extended quantization balancing memory use and inference speed. |
|
| 83 |
+
| [**model-Q4_0_8_8.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-Q4_0_8_8.gguf) | Advanced memory precision targeting larger contexts. |
|
| 84 |
+
| [**model-Q4_K_M.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-Q4_K_M.gguf) | High-efficiency quantization for moderate GPU resources. |
|
| 85 |
+
| [**model-Q4_K_S.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-Q4_K_S.gguf) | Optimized for smaller-scale operations with compact memory footprint. |
|
| 86 |
+
| [**model-Q5_K_M.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-Q5_K_M.gguf) | Balances performance and precision, ideal for robust inferencing environments. |
|
| 87 |
+
| [**model-Q5_K_S.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-Q5_K_S.gguf) | Moderate quantization targeting performance with minimal resource usage. |
|
| 88 |
+
| [**model-Q6_K.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-Q6_K.gguf) | High-precision quantization for accurate and stable inferencing tasks. |
|
| 89 |
+
| [**model-TQ1_0.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-TQ1_0.gguf) | Experimental quantization for targeted applications in test environments. |
|
| 90 |
+
| [**model-TQ2_0.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-TQ2_0.gguf) | High-performance tuning for experimental use cases and flexible precision. |
|
| 91 |
|
| 92 |
+
---
|
| 93 |
### Datasets and Fine-Tuning
|
| 94 |
|
| 95 |
The following fine-tuning datasets are leveraged to enhance specific model capabilities:
|