## nvidia/Llama3-ChatQA-1.5-8B - GGUF
This repo contains GGUF format model files for [nvidia/Llama3-ChatQA-1.5-8B](https://huggingface.co/nvidia/Llama3-ChatQA-1.5-8B).
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
## Prompt template
```
<|begin_of_text|>System: This is a chat between a user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions based on the context. The assistant should also indicate when the answer cannot be found in the context.
User: {prompt}
Assistant:
```
## Model file specification
| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [Llama3-ChatQA-1.5-8B-Q2_K.gguf](https://huggingface.co/tensorblock/Llama3-ChatQA-1.5-8B-GGUF/tree/main/Llama3-ChatQA-1.5-8B-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
| [Llama3-ChatQA-1.5-8B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama3-ChatQA-1.5-8B-GGUF/tree/main/Llama3-ChatQA-1.5-8B-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
| [Llama3-ChatQA-1.5-8B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama3-ChatQA-1.5-8B-GGUF/tree/main/Llama3-ChatQA-1.5-8B-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
| [Llama3-ChatQA-1.5-8B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama3-ChatQA-1.5-8B-GGUF/tree/main/Llama3-ChatQA-1.5-8B-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
| [Llama3-ChatQA-1.5-8B-Q4_0.gguf](https://huggingface.co/tensorblock/Llama3-ChatQA-1.5-8B-GGUF/tree/main/Llama3-ChatQA-1.5-8B-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [Llama3-ChatQA-1.5-8B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama3-ChatQA-1.5-8B-GGUF/tree/main/Llama3-ChatQA-1.5-8B-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
| [Llama3-ChatQA-1.5-8B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama3-ChatQA-1.5-8B-GGUF/tree/main/Llama3-ChatQA-1.5-8B-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
| [Llama3-ChatQA-1.5-8B-Q5_0.gguf](https://huggingface.co/tensorblock/Llama3-ChatQA-1.5-8B-GGUF/tree/main/Llama3-ChatQA-1.5-8B-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [Llama3-ChatQA-1.5-8B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama3-ChatQA-1.5-8B-GGUF/tree/main/Llama3-ChatQA-1.5-8B-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
| [Llama3-ChatQA-1.5-8B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama3-ChatQA-1.5-8B-GGUF/tree/main/Llama3-ChatQA-1.5-8B-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
| [Llama3-ChatQA-1.5-8B-Q6_K.gguf](https://huggingface.co/tensorblock/Llama3-ChatQA-1.5-8B-GGUF/tree/main/Llama3-ChatQA-1.5-8B-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
| [Llama3-ChatQA-1.5-8B-Q8_0.gguf](https://huggingface.co/tensorblock/Llama3-ChatQA-1.5-8B-GGUF/tree/main/Llama3-ChatQA-1.5-8B-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
## Downloading instruction
### Command line
Firstly, install Huggingface Client
```shell
pip install -U "huggingface_hub[cli]"
```
Then, downoad the individual model file the a local directory
```shell
huggingface-cli download tensorblock/Llama3-ChatQA-1.5-8B-GGUF --include "Llama3-ChatQA-1.5-8B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
```
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
```shell
huggingface-cli download tensorblock/Llama3-ChatQA-1.5-8B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
