--- language: - ko - en base_model: lcw99/zephykor-ko-7b-chang tags: - TensorBlock - GGUF ---
TensorBlock

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

## lcw99/zephykor-ko-7b-chang - GGUF This repo contains GGUF format model files for [lcw99/zephykor-ko-7b-chang](https://huggingface.co/lcw99/zephykor-ko-7b-chang). 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).
Run them on the TensorBlock client using your local machine ↗
## Prompt template ``` <|system|> {system_prompt} <|user|> {prompt} <|assistant|> ``` ## Model file specification | Filename | Quant type | File Size | Description | | -------- | ---------- | --------- | ----------- | | [zephykor-ko-7b-chang-Q2_K.gguf](https://huggingface.co/tensorblock/zephykor-ko-7b-chang-GGUF/blob/main/zephykor-ko-7b-chang-Q2_K.gguf) | Q2_K | 2.602 GB | smallest, significant quality loss - not recommended for most purposes | | [zephykor-ko-7b-chang-Q3_K_S.gguf](https://huggingface.co/tensorblock/zephykor-ko-7b-chang-GGUF/blob/main/zephykor-ko-7b-chang-Q3_K_S.gguf) | Q3_K_S | 3.023 GB | very small, high quality loss | | [zephykor-ko-7b-chang-Q3_K_M.gguf](https://huggingface.co/tensorblock/zephykor-ko-7b-chang-GGUF/blob/main/zephykor-ko-7b-chang-Q3_K_M.gguf) | Q3_K_M | 3.353 GB | very small, high quality loss | | [zephykor-ko-7b-chang-Q3_K_L.gguf](https://huggingface.co/tensorblock/zephykor-ko-7b-chang-GGUF/blob/main/zephykor-ko-7b-chang-Q3_K_L.gguf) | Q3_K_L | 3.635 GB | small, substantial quality loss | | [zephykor-ko-7b-chang-Q4_0.gguf](https://huggingface.co/tensorblock/zephykor-ko-7b-chang-GGUF/blob/main/zephykor-ko-7b-chang-Q4_0.gguf) | Q4_0 | 3.910 GB | legacy; small, very high quality loss - prefer using Q3_K_M | | [zephykor-ko-7b-chang-Q4_K_S.gguf](https://huggingface.co/tensorblock/zephykor-ko-7b-chang-GGUF/blob/main/zephykor-ko-7b-chang-Q4_K_S.gguf) | Q4_K_S | 3.940 GB | small, greater quality loss | | [zephykor-ko-7b-chang-Q4_K_M.gguf](https://huggingface.co/tensorblock/zephykor-ko-7b-chang-GGUF/blob/main/zephykor-ko-7b-chang-Q4_K_M.gguf) | Q4_K_M | 4.152 GB | medium, balanced quality - recommended | | [zephykor-ko-7b-chang-Q5_0.gguf](https://huggingface.co/tensorblock/zephykor-ko-7b-chang-GGUF/blob/main/zephykor-ko-7b-chang-Q5_0.gguf) | Q5_0 | 4.746 GB | legacy; medium, balanced quality - prefer using Q4_K_M | | [zephykor-ko-7b-chang-Q5_K_S.gguf](https://huggingface.co/tensorblock/zephykor-ko-7b-chang-GGUF/blob/main/zephykor-ko-7b-chang-Q5_K_S.gguf) | Q5_K_S | 4.746 GB | large, low quality loss - recommended | | [zephykor-ko-7b-chang-Q5_K_M.gguf](https://huggingface.co/tensorblock/zephykor-ko-7b-chang-GGUF/blob/main/zephykor-ko-7b-chang-Q5_K_M.gguf) | Q5_K_M | 4.870 GB | large, very low quality loss - recommended | | [zephykor-ko-7b-chang-Q6_K.gguf](https://huggingface.co/tensorblock/zephykor-ko-7b-chang-GGUF/blob/main/zephykor-ko-7b-chang-Q6_K.gguf) | Q6_K | 5.633 GB | very large, extremely low quality loss | | [zephykor-ko-7b-chang-Q8_0.gguf](https://huggingface.co/tensorblock/zephykor-ko-7b-chang-GGUF/blob/main/zephykor-ko-7b-chang-Q8_0.gguf) | Q8_0 | 7.296 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/zephykor-ko-7b-chang-GGUF --include "zephykor-ko-7b-chang-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/zephykor-ko-7b-chang-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf' ```