Upload folder using huggingface_hub

README.md

@@ -20,9 +20,9 @@ A collection of optimized GGUF quantized models derived from [bloomvn-0.5b-ppo](
 
 | Variant | Use Case | Download |
 |---------|-----------|------------|
-| base | This FP16 format model is ideal for applications where high accuracy is crucial and storage space is not a concern, such as in data centers or high-performance computing environments. | [📥](https://huggingface.co/Vuanhngo11/bloomvn-0.5b-ppo-gguf/resolve/main/base.gguf)
-| q2_k | The 2-bit quantized model is suitable for extremely constrained environments, such as low-power edge devices or those with very limited memory, where a balance between size and performance is necessary. | [📥](https://huggingface.co/Vuanhngo11/bloomvn-0.5b-ppo-gguf/resolve/main/q2_k.gguf)
-| q3_k_m | The 3-bit quantized model offers a good balance between compression and performance, making it suitable for memory-limited devices that still require a reasonable level of accuracy, such as mid-range smartphones or embedded systems. | [📥](https://huggingface.co/Vuanhngo11/bloomvn-0.5b-ppo-gguf/resolve/main/q3_k_m.gguf)
+| base | The base model is suitable for applications where model size is not a concern, and high accuracy is required. It can be used for tasks such as text generation, language translation, and text summarization. This model is in FP16 format, providing a good balance between size and performance. | [📥](https://huggingface.co/Vuanhngo11/bloomvn-0.5b-ppo-gguf/resolve/main/base.gguf)
+| q2_k | The q2_k variant is ideal for extremely constrained environments where model size is a significant concern, such as embedded systems or low-end mobile devices. Although it is highly compressed, it still maintains a reasonable level of accuracy, making it suitable for simple language tasks. This 2-bit quantized model is a good choice when storage space is limited. | [📥](https://huggingface.co/Vuanhngo11/bloomvn-0.5b-ppo-gguf/resolve/main/q2_k.gguf)
+| q3_k_m | The q3_k_m variant is designed for memory-limited devices that require a balance between model size and accuracy. This 3-bit quantized model is very compressed, making it suitable for mid-range mobile devices or systems with limited storage capacity. It is a good choice for applications where a moderate level of accuracy is required, such as language understanding or text classification. | [📥](https://huggingface.co/Vuanhngo11/bloomvn-0.5b-ppo-gguf/resolve/main/q3_k_m.gguf)
 
 ## 🤝 Contributors