Downloads · 30 days
25
10% of all-time downloads
Dracones/CodeQwen1.5-7B_exl2_7.0bpw
CodeQwen1.5-7B_exl2_7.0bpw is a text generation model from Dracones. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
This is a 7.0bpw EXL2 quant of Qwen/CodeQwen1.5-7B
Downloads · 30 days
25
10% of all-time downloads
All-time downloads
253
Public
Repo size
6.7 GB
Likes
0
Public
Click a slice to open those files.
.safetensors6.7 GB · 100%
From the Hugging Face model README
This is a 7.0bpw EXL2 quant of Qwen/CodeQwen1.5-7B
Details about the model can be found at the above model page.
These quants were made with exllamav2 version 0.0.18. Quants made on this version of EXL2 may not work on older versions of the exllamav2 library.
If you have problems loading these models, please update Text Generation WebUI to the latest version.
Below are the perplexity scores for the EXL2 models. A lower score is better.
| Quant Level | Perplexity Score |
|---|---|
| 8.0 | 10.8767 |
| 7.0 | 10.8824 |
| 6.0 | 10.8876 |
| 5.0 | 10.9341 |
| 4.0 | 11.1726 |
| 3.5 | 11.4286 |
| 3.0 | 12.3887 |
| 2.75 | 12.8403 |
| 2.5 | 13.6661 |
This was the script used for perplexity testing.
#!/bin/bash
source ~/miniconda3/etc/profile.d/conda.sh
conda activate exllamav2
# Set the model name and bit size
MODEL_NAME="CodeQwen1.5-7B"
BIT_PRECISIONS=(8.0 7.0 6.0 5.0 4.0 3.5 3.0 2.75 2.5)
# Print the markdown table header
echo "| Quant Level | Perplexity Score |"
echo "|-------------|------------------|"
for BIT_PRECISION in "${BIT_PRECISIONS[@]}"
do
MODEL_DIR="models/${MODEL_NAME}_exl2_${BIT_PRECISION}bpw"
if [ -d "$MODEL_DIR" ]; then
output=$(python test_inference.py -m "$MODEL_DIR" -gs 17,24 -ed data/wikitext/wikitext-2-v1.parquet)
score=$(echo "$output" | grep -oP 'Evaluation perplexity: \K[\d.]+')
echo "| $BIT_PRECISION | $score |"
fi
done
This is the script used for quantization.
#!/bin/bash
# Activate the conda environment
source ~/miniconda3/etc/profile.d/conda.sh
conda activate exllamav2
# Set the model name and bit size
MODEL_NAME="CodeQwen1.5-7B"
# Define variables
MODEL_DIR="models/$MODEL_NAME"
OUTPUT_DIR="exl2_$MODEL_NAME"
MEASUREMENT_FILE="measurements/$MODEL_NAME.json"
# Create the measurement file if needed
if [ ! -f "$MEASUREMENT_FILE" ]; then
echo "Creating $MEASUREMENT_FILE"
# Create directories
if [ -d "$OUTPUT_DIR" ]; then
rm -r "$OUTPUT_DIR"
fi
mkdir "$OUTPUT_DIR"
python convert.py -i $MODEL_DIR -o $OUTPUT_DIR -nr -om $MEASUREMENT_FILE
fi
# Choose one of the below. Either create a single quant for testing or a batch of them.
# BIT_PRECISIONS=(2.25)
BIT_PRECISIONS=(8.0 7.0 6.0 5.0 4.0 3.5 3.0 2.75 2.5)
for BIT_PRECISION in "${BIT_PRECISIONS[@]}"
do
CONVERTED_FOLDER="models/${MODEL_NAME}_exl2_${BIT_PRECISION}bpw"
# If it doesn't already exist, make the quant
if [ ! -d "$CONVERTED_FOLDER" ]; then
echo "Creating $CONVERTED_FOLDER"
# Create directories
if [ -d "$OUTPUT_DIR" ]; then
rm -r "$OUTPUT_DIR"
fi
mkdir "$OUTPUT_DIR"
mkdir "$CONVERTED_FOLDER"
# Run conversion commands
python convert.py -i $MODEL_DIR -o $OUTPUT_DIR -nr -m $MEASUREMENT_FILE -b $BIT_PRECISION -cf $CONVERTED_FOLDER
fi
done