|
--- |
|
base_model: sronger/ko-llm-llama-2-7b-chat3 |
|
tags: |
|
- TensorBlock |
|
- GGUF |
|
--- |
|
|
|
<div style="width: auto; margin-left: auto; margin-right: auto"> |
|
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;"> |
|
</div> |
|
<div style="display: flex; justify-content: space-between; width: 100%;"> |
|
<div style="display: flex; flex-direction: column; align-items: flex-start;"> |
|
<p style="margin-top: 0.5em; margin-bottom: 0em;"> |
|
Feedback and support: TensorBlock's <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a> |
|
</p> |
|
</div> |
|
</div> |
|
|
|
## sronger/ko-llm-llama-2-7b-chat3 - GGUF |
|
|
|
This repo contains GGUF format model files for [sronger/ko-llm-llama-2-7b-chat3](https://huggingface.co/sronger/ko-llm-llama-2-7b-chat3). |
|
|
|
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). |
|
|
|
|
|
<div style="text-align: left; margin: 20px 0;"> |
|
<a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;"> |
|
Run them on the TensorBlock client using your local machine ↗ |
|
</a> |
|
</div> |
|
|
|
## Prompt template |
|
|
|
|
|
``` |
|
|
|
``` |
|
|
|
## Model file specification |
|
|
|
| Filename | Quant type | File Size | Description | |
|
| -------- | ---------- | --------- | ----------- | |
|
| [ko-llm-llama-2-7b-chat3-Q2_K.gguf](https://huggingface.co/tensorblock/ko-llm-llama-2-7b-chat3-GGUF/blob/main/ko-llm-llama-2-7b-chat3-Q2_K.gguf) | Q2_K | 0.221 GB | smallest, significant quality loss - not recommended for most purposes | |
|
| [ko-llm-llama-2-7b-chat3-Q3_K_S.gguf](https://huggingface.co/tensorblock/ko-llm-llama-2-7b-chat3-GGUF/blob/main/ko-llm-llama-2-7b-chat3-Q3_K_S.gguf) | Q3_K_S | 0.259 GB | very small, high quality loss | |
|
| [ko-llm-llama-2-7b-chat3-Q3_K_M.gguf](https://huggingface.co/tensorblock/ko-llm-llama-2-7b-chat3-GGUF/blob/main/ko-llm-llama-2-7b-chat3-Q3_K_M.gguf) | Q3_K_M | 0.284 GB | very small, high quality loss | |
|
| [ko-llm-llama-2-7b-chat3-Q3_K_L.gguf](https://huggingface.co/tensorblock/ko-llm-llama-2-7b-chat3-GGUF/blob/main/ko-llm-llama-2-7b-chat3-Q3_K_L.gguf) | Q3_K_L | 0.306 GB | small, substantial quality loss | |
|
| [ko-llm-llama-2-7b-chat3-Q4_0.gguf](https://huggingface.co/tensorblock/ko-llm-llama-2-7b-chat3-GGUF/blob/main/ko-llm-llama-2-7b-chat3-Q4_0.gguf) | Q4_0 | 0.333 GB | legacy; small, very high quality loss - prefer using Q3_K_M | |
|
| [ko-llm-llama-2-7b-chat3-Q4_K_S.gguf](https://huggingface.co/tensorblock/ko-llm-llama-2-7b-chat3-GGUF/blob/main/ko-llm-llama-2-7b-chat3-Q4_K_S.gguf) | Q4_K_S | 0.335 GB | small, greater quality loss | |
|
| [ko-llm-llama-2-7b-chat3-Q4_K_M.gguf](https://huggingface.co/tensorblock/ko-llm-llama-2-7b-chat3-GGUF/blob/main/ko-llm-llama-2-7b-chat3-Q4_K_M.gguf) | Q4_K_M | 0.355 GB | medium, balanced quality - recommended | |
|
| [ko-llm-llama-2-7b-chat3-Q5_0.gguf](https://huggingface.co/tensorblock/ko-llm-llama-2-7b-chat3-GGUF/blob/main/ko-llm-llama-2-7b-chat3-Q5_0.gguf) | Q5_0 | 0.402 GB | legacy; medium, balanced quality - prefer using Q4_K_M | |
|
| [ko-llm-llama-2-7b-chat3-Q5_K_S.gguf](https://huggingface.co/tensorblock/ko-llm-llama-2-7b-chat3-GGUF/blob/main/ko-llm-llama-2-7b-chat3-Q5_K_S.gguf) | Q5_K_S | 0.402 GB | large, low quality loss - recommended | |
|
| [ko-llm-llama-2-7b-chat3-Q5_K_M.gguf](https://huggingface.co/tensorblock/ko-llm-llama-2-7b-chat3-GGUF/blob/main/ko-llm-llama-2-7b-chat3-Q5_K_M.gguf) | Q5_K_M | 0.414 GB | large, very low quality loss - recommended | |
|
| [ko-llm-llama-2-7b-chat3-Q6_K.gguf](https://huggingface.co/tensorblock/ko-llm-llama-2-7b-chat3-GGUF/blob/main/ko-llm-llama-2-7b-chat3-Q6_K.gguf) | Q6_K | 0.476 GB | very large, extremely low quality loss | |
|
| [ko-llm-llama-2-7b-chat3-Q8_0.gguf](https://huggingface.co/tensorblock/ko-llm-llama-2-7b-chat3-GGUF/blob/main/ko-llm-llama-2-7b-chat3-Q8_0.gguf) | Q8_0 | 0.617 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/ko-llm-llama-2-7b-chat3-GGUF --include "ko-llm-llama-2-7b-chat3-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/ko-llm-llama-2-7b-chat3-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf' |
|
``` |
|
|
