metadata

base_model: https://huggingface.co/Phind/Phind-CodeLlama-34B-v2
inference: false
license: llama2
model_creator: https://huggingface.co/Phind
model_name: Phind-Codellama-34B-v2
model_type: llama
quantized_by: latimar

Phind-CodeLlama-34B-v2 EXL2

Weights of Phind-CodeLlama-34B-v2 converted to EXL2 format.

Converted with the ExllamaV2 convert.py script, exllamav2 commit

BPW (hb=8)	Human-Eval	Evol-Ins PPL	Wiki PPL	File Size (Gb)
2.55	0.402439	2.0944	18.9843	10.62
2.8	0.634146	2.0814	17.6326	11.58
3.0	0.664634	2.0600	11.2096	12.36
4.625	0.701219	2.0401	6.7243	18.63

Datasets used for calibration and PPL measurement

Conversion

Conversion arguments:

convert.py -i ${MODEL_DIR_FP16} -o ${WIP_DIR} -cf ${MODEL_DIR_EXL} -c ${CALIBRATION_DATASET} -r 200 -mr 32 -l 4096 -ml 4096 -hb 8 -b ${BPW}

2.55 quant was converted using even more raws: -r 400 -mr 64

Perplexity

Perplexity was measured with test_inference.py script:

test_inference.py -m ${MODEL_DIR_EXL} -ed ${PPL_DATASET}

Human-Eval

For the point of reference, Phind says that the original model achieves 73.8 Human-Eval score.

Samples for the Human-Eval scores of EXL2 quants were generated with exl2.human-eval.py script:

python exl2.human-eval.py -m ${MODEL_DIR_EXL2} -c 4096 -o ${BPW}-samples.jsonl

Unfortunately, FP16/INT8 weights of this model won't fit on my RTX 4090, but FP16 quantized to NF4 fits, so I generated samples with tf.human-eval.py script:

python tf.human-eval.py -m ${MODEL_DIR_FP16} -o nf4-samples.jsonl

NF4 variant gives us 0.70731707

As another reference, EXL2 3.2-bpw quant of this model by firelzrd yields 0.609756 Human-Eval score.