metadata
base_model: cfahlgren1/NaturalSQL-6.7B-v0
tags:
- instruct
- finetune
- TensorBlock
- GGUF
license: other
license_name: deepseek
language:
- en
datasets:
- cfahlgren1/wiki-sql-codellama-expanded
- cfahlgren1/natural-sql
model-index:
- name: NaturalSQL-6.7B-v0.1
results: []
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
cfahlgren1/NaturalSQL-6.7B-v0 - GGUF
This repo contains GGUF format model files for cfahlgren1/NaturalSQL-6.7B-v0.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.
Prompt template
<｜begin▁of▁sentence｜>{system_prompt}### Instruction:
{prompt}
### Response:
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| NaturalSQL-6.7B-v0-Q2_K.gguf | Q2_K | 2.535 GB | smallest, significant quality loss - not recommended for most purposes |
| NaturalSQL-6.7B-v0-Q3_K_S.gguf | Q3_K_S | 2.950 GB | very small, high quality loss |
| NaturalSQL-6.7B-v0-Q3_K_M.gguf | Q3_K_M | 3.300 GB | very small, high quality loss |
| NaturalSQL-6.7B-v0-Q3_K_L.gguf | Q3_K_L | 3.599 GB | small, substantial quality loss |
| NaturalSQL-6.7B-v0-Q4_0.gguf | Q4_0 | 3.828 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| NaturalSQL-6.7B-v0-Q4_K_S.gguf | Q4_K_S | 3.859 GB | small, greater quality loss |
| NaturalSQL-6.7B-v0-Q4_K_M.gguf | Q4_K_M | 4.083 GB | medium, balanced quality - recommended |
| NaturalSQL-6.7B-v0-Q5_0.gguf | Q5_0 | 4.654 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| NaturalSQL-6.7B-v0-Q5_K_S.gguf | Q5_K_S | 4.654 GB | large, low quality loss - recommended |
| NaturalSQL-6.7B-v0-Q5_K_M.gguf | Q5_K_M | 4.785 GB | large, very low quality loss - recommended |
| NaturalSQL-6.7B-v0-Q6_K.gguf | Q6_K | 5.531 GB | very large, extremely low quality loss |
| NaturalSQL-6.7B-v0-Q8_0.gguf | Q8_0 | 7.164 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/NaturalSQL-6.7B-v0-GGUF --include "NaturalSQL-6.7B-v0-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/NaturalSQL-6.7B-v0-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'