metadata
base_model: INSAIT-Institute/BgGPT-7B-Instruct-v0.2
tags:
- mistral
- instruct
- bggpt
- insait
- TensorBlock
- GGUF
language:
- bg
- en
library_name: transformers
pipeline_tag: text-generation
license: apache-2.0
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
INSAIT-Institute/BgGPT-7B-Instruct-v0.2 - GGUF
This repo contains GGUF format model files for INSAIT-Institute/BgGPT-7B-Instruct-v0.2.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Prompt template
<s>[INST] {prompt} [/INST]
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| BgGPT-7B-Instruct-v0.2-Q2_K.gguf | Q2_K | 2.559 GB | smallest, significant quality loss - not recommended for most purposes |
| BgGPT-7B-Instruct-v0.2-Q3_K_S.gguf | Q3_K_S | 2.976 GB | very small, high quality loss |
| BgGPT-7B-Instruct-v0.2-Q3_K_M.gguf | Q3_K_M | 3.306 GB | very small, high quality loss |
| BgGPT-7B-Instruct-v0.2-Q3_K_L.gguf | Q3_K_L | 3.588 GB | small, substantial quality loss |
| BgGPT-7B-Instruct-v0.2-Q4_0.gguf | Q4_0 | 3.859 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| BgGPT-7B-Instruct-v0.2-Q4_K_S.gguf | Q4_K_S | 3.888 GB | small, greater quality loss |
| BgGPT-7B-Instruct-v0.2-Q4_K_M.gguf | Q4_K_M | 4.100 GB | medium, balanced quality - recommended |
| BgGPT-7B-Instruct-v0.2-Q5_0.gguf | Q5_0 | 4.689 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| BgGPT-7B-Instruct-v0.2-Q5_K_S.gguf | Q5_K_S | 4.689 GB | large, low quality loss - recommended |
| BgGPT-7B-Instruct-v0.2-Q5_K_M.gguf | Q5_K_M | 4.814 GB | large, very low quality loss - recommended |
| BgGPT-7B-Instruct-v0.2-Q6_K.gguf | Q6_K | 5.572 GB | very large, extremely low quality loss |
| BgGPT-7B-Instruct-v0.2-Q8_0.gguf | Q8_0 | 7.216 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/BgGPT-7B-Instruct-v0.2-GGUF --include "BgGPT-7B-Instruct-v0.2-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/BgGPT-7B-Instruct-v0.2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'