Quant Level	Perplexity Score	Repo
6.0	4.7068	turboderp
5.5	4.7136	Dracones
5.0	4.7309	turboderp
4.5	4.8111	turboderp
4.25	4.8292	turboderp
4.0	4.8603	turboderp
3.75	4.9112	turboderp
3.5	4.9592	turboderp
3.25	5.0631	turboderp
3.0	5.2050	turboderp
2.75	5.3820	Dracones
2.5	5.6681	turboderp
2.25	5.9769	Dracones

EQ Bench

Here are the EQ Bench scores for the EXL2 quants using Alpaca, ChatML, Command-R and Command-R-Plus prompt templates. A higher score is better.

Quant Size	Alpaca	ChatML	Command-R	Command-R-Plus
6.0	70.77	62.58	75.81	74.95
5.5	71.93	67.7	74.9	75.48
5.0	69.51	63.94	74.92	75.28

Note: EQ Bench scripting not working well, other quants may not be tested.

Command-R-Plus Template

This is the Command-R-Plus template yaml that was used in EQ bench(which uses Text Generation Web UI yaml templates). It adds BOS_TOKEN into the starter prompt.

text-generation-webui/instruction-templates/Command-R-Plus.yaml:

yaml

instruction_template: |-
  {%- if messages[0]['role'] == 'system' -%}
      {%- set loop_messages = messages[1:] -%}
      {%- set system_message = messages[0]['content'] -%}
  {%- elif false == true -%}
      {%- set loop_messages = messages -%}
      {%- set system_message = 'You are Command-R, a brilliant, sophisticated, AI-assistant trained to assist human users by providing thorough responses. You are trained by Cohere.' -%}
  {%- else -%}
      {%- set loop_messages = messages -%}
      {%- set system_message = false -%}
  {%- endif -%}
  {%- if system_message != false -%}
      {{ '<BOS_TOKEN><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}
  {%- endif -%}
  {%- for message in loop_messages -%}
      {%- set content = message['content'] -%}
      {%- if message['role'] == 'user' -%}
          {{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}
      {%- elif message['role'] == 'assistant' -%}
          {{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>'  + content.strip() + '<|END_OF_TURN_TOKEN|>' }}
      {%- endif -%}
  {%- endfor -%}
  {%- if add_generation_prompt -%}
      {{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}
  {%- endif -%}

Perplexity Script

This was the script used for perplexity testing.

bash

#!/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="c4ai-command-r-plus"
BIT_PRECISIONS=(8.0 7.5 7.0 6.5 5.5 2.75 2.25)

# MODEL_NAME="turboderp_command-r-plus-103B"
# BIT_PRECISIONS=(6.0 5.0 4.5 4.25 4.0 3.75 3.5 3.25 3.0 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_${BIT_PRECISION}bpw"
#   MODEL_DIR="models/${MODEL_NAME}-exl2_${BIT_PRECISION}bpw"
  if [ -d "$MODEL_DIR" ]; then
    output=$(python test_inference.py -m "$MODEL_DIR" -gs 22,24 -ed data/wikitext/wikitext-2-v1.parquet)
    score=$(echo "$output" | grep -oP 'Evaluation perplexity: \K[\d.]+')
    echo "| $BIT_PRECISION | $score |"
  fi
done

Quant Details

This is the script used for quantization.

bash

#!/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="c4ai-command-r-plus"

# 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=(5.0)
BIT_PRECISIONS=(8.0 7.5 6.5 5.5 2.75 2.25)

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

Dracones/c4ai-command-r-plus_exl2_2.75bpw

c4ai-command-r-plus - EXL2 2.75bpw

Turbodep EXL2 Quants

EXL2 Version

Perplexity Scoring

EQ Bench

Command-R-Plus Template

Perplexity Script

Quant Details

Dracones/
c4ai-command-r-plus_exl2_2.75bpw