metadata
library_name: transformers
datasets:
- premai-io/spider
- premai-io/domains
- premai-io/birdbench
- gretelai/synthetic_text_to_sql
metrics:
- accuracy
base_model: premai-io/prem-1B-SQL
pipeline_tag: text2text-generation
tags:
- TensorBlock
- GGUF
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
premai-io/prem-1B-SQL - GGUF
This repo contains GGUF format model files for premai-io/prem-1B-SQL.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Prompt template
<｜begin▁of▁sentence｜>{system_prompt}### Instruction:
{prompt}
### Response:
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| prem-1B-SQL-Q2_K.gguf | Q2_K | 0.521 GB | smallest, significant quality loss - not recommended for most purposes |
| prem-1B-SQL-Q3_K_S.gguf | Q3_K_S | 0.598 GB | very small, high quality loss |
| prem-1B-SQL-Q3_K_M.gguf | Q3_K_M | 0.656 GB | very small, high quality loss |
| prem-1B-SQL-Q3_K_L.gguf | Q3_K_L | 0.693 GB | small, substantial quality loss |
| prem-1B-SQL-Q4_0.gguf | Q4_0 | 0.723 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| prem-1B-SQL-Q4_K_S.gguf | Q4_K_S | 0.758 GB | small, greater quality loss |
| prem-1B-SQL-Q4_K_M.gguf | Q4_K_M | 0.813 GB | medium, balanced quality - recommended |
| prem-1B-SQL-Q5_0.gguf | Q5_0 | 0.872 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| prem-1B-SQL-Q5_K_S.gguf | Q5_K_S | 0.887 GB | large, low quality loss - recommended |
| prem-1B-SQL-Q5_K_M.gguf | Q5_K_M | 0.933 GB | large, very low quality loss - recommended |
| prem-1B-SQL-Q6_K.gguf | Q6_K | 1.091 GB | very large, extremely low quality loss |
| prem-1B-SQL-Q8_0.gguf | Q8_0 | 1.334 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/prem-1B-SQL-GGUF --include "prem-1B-SQL-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/prem-1B-SQL-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'