metadata
datasets:
- beomi/KoAlpaca-v1.1a
- dbdu/ShareGPT-74k-ko
- heegyu/korquad-chat-v1
- HAERAE-HUB/KoInstruct-QA
- changpt/ko-lima-vicuna
- nlpai-lab/kullm-v2
language:
- ko
tags:
- TensorBlock
- GGUF
base_model: heegyu/llama-2-ko-7b-chat
heegyu/llama-2-ko-7b-chat - GGUF
This repo contains GGUF format model files for heegyu/llama-2-ko-7b-chat.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b5165.
Our projects
| Awesome MCP Servers | TensorBlock Studio |
|---|---|
 |
 |
| A comprehensive collection of Model Context Protocol (MCP) servers. | A lightweight, open, and extensible multi-LLM interaction studio. |
| 👀 See what we built 👀 | 👀 See what we built 👀 |
Prompt template
Unable to determine prompt format automatically. Please check the original model repository for the correct prompt format.
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| llama-2-ko-7b-chat-Q2_K.gguf | Q2_K | 2.601 GB | smallest, significant quality loss - not recommended for most purposes |
| llama-2-ko-7b-chat-Q3_K_S.gguf | Q3_K_S | 3.022 GB | very small, high quality loss |
| llama-2-ko-7b-chat-Q3_K_M.gguf | Q3_K_M | 3.372 GB | very small, high quality loss |
| llama-2-ko-7b-chat-Q3_K_L.gguf | Q3_K_L | 3.671 GB | small, substantial quality loss |
| llama-2-ko-7b-chat-Q4_0.gguf | Q4_0 | 3.907 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| llama-2-ko-7b-chat-Q4_K_S.gguf | Q4_K_S | 3.938 GB | small, greater quality loss |
| llama-2-ko-7b-chat-Q4_K_M.gguf | Q4_K_M | 4.163 GB | medium, balanced quality - recommended |
| llama-2-ko-7b-chat-Q5_0.gguf | Q5_0 | 4.741 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| llama-2-ko-7b-chat-Q5_K_S.gguf | Q5_K_S | 4.741 GB | large, low quality loss - recommended |
| llama-2-ko-7b-chat-Q5_K_M.gguf | Q5_K_M | 4.872 GB | large, very low quality loss - recommended |
| llama-2-ko-7b-chat-Q6_K.gguf | Q6_K | 5.626 GB | very large, extremely low quality loss |
| llama-2-ko-7b-chat-Q8_0.gguf | Q8_0 | 7.286 GB | very large, extremely low quality loss - not recommended |
Downloading instruction
Command line
Firstly, install Huggingface Client
pip install -U "huggingface_hub[cli]"
Then, downoad the individual model file the a local directory
huggingface-cli download tensorblock/heegyu_llama-2-ko-7b-chat-GGUF --include "llama-2-ko-7b-chat-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:
huggingface-cli download tensorblock/heegyu_llama-2-ko-7b-chat-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'