mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-11-11 21:39:52 +00:00
b9fd7eee57
* ggml : remove Q4_0 bit shufling (ARM NEON)
* ggml : remove Q4_1 bit shuffling (ARM NEON + reference)
* ggml : nibbles_from_floats() + bytes_from_nibbles() (ARM NEON)
* ggml : remove Q4_2 bit shuffling (WIP, BROKEN)
* ggml : remove Q5_0 bit shuffling (ARM NEON)
* ggml : 2x faster scalar implementations
* ggml : remove Q5_1 bit shuffling (ARM NEON + scalar)
* ggml : simplify scalar dot
* ggml : remove WASM SIMD bit shuffling + remove vzip for ARM 32-bit
* ggml : fix Q4_1 quantization
* ggml : update cuBLAS + normalize variable names
* ggml : remove Q4_2 mode
* ggml : minor formatting
* ggml : fix Q5_0 quantization
* scripts : add script for measuring the time per token
* AVX implementations (#1370)
* ggml : uniform 5th bit extraction
* llama : produce error upon loading old model files
* llama : fix model magic/version write
* ggml : speed-up Q5_0 + Q5_1 at 4 threads
* ggml : preserve old Q4 and Q5 formats
* ggml : simplify Q8_1 - no need for low / high sums anymore
* ggml : fix Q8_0 and Q8_1 rounding
* Revert "AVX implementations (#1370)"
This reverts commit 948d124837.
* ggml : fix AVX2 implementation
* sha : update hashes for 7B and 13B
* readme : update timings + remove warning banner
* llama : update v2 PR number to 1405
* ggml : fix WASM comments
* ggml : back to original bit order
* readme : add note that Q4 and Q5 have been changed
* llama : fix return for unknown version
---------
Co-authored-by: Stephan Walter <stephan@walter.name>
40 lines
2.7 KiB
Bash
Executable File
40 lines
2.7 KiB
Bash
Executable File
#!/bin/bash
|
|
|
|
#
|
|
# quantize
|
|
#
|
|
|
|
# 7B
|
|
time ./bin/quantize ../models/7B/ggml-model-f16.bin ../models/7B/ggml-model-q4_0.bin q4_0 2>&1 | tee ../qnt-7b-q4_0.txt
|
|
time ./bin/quantize ../models/7B/ggml-model-f16.bin ../models/7B/ggml-model-q4_1.bin q4_1 2>&1 | tee ../qnt-7b-q4_1.txt
|
|
time ./bin/quantize ../models/7B/ggml-model-f16.bin ../models/7B/ggml-model-q5_0.bin q5_0 2>&1 | tee ../qnt-7b-q5_0.txt
|
|
time ./bin/quantize ../models/7B/ggml-model-f16.bin ../models/7B/ggml-model-q5_1.bin q5_1 2>&1 | tee ../qnt-7b-q5_1.txt
|
|
time ./bin/quantize ../models/7B/ggml-model-f16.bin ../models/7B/ggml-model-q8_0.bin q8_0 2>&1 | tee ../qnt-7b-q8_0.txt
|
|
|
|
# 13B
|
|
time ./bin/quantize ../models/13B/ggml-model-f16.bin ../models/13B/ggml-model-q4_0.bin q4_0 2>&1 | tee ../qnt-13b-q4_0.txt
|
|
time ./bin/quantize ../models/13B/ggml-model-f16.bin ../models/13B/ggml-model-q4_1.bin q4_1 2>&1 | tee ../qnt-13b-q4_1.txt
|
|
time ./bin/quantize ../models/13B/ggml-model-f16.bin ../models/13B/ggml-model-q5_0.bin q5_0 2>&1 | tee ../qnt-13b-q5_0.txt
|
|
time ./bin/quantize ../models/13B/ggml-model-f16.bin ../models/13B/ggml-model-q5_1.bin q5_1 2>&1 | tee ../qnt-13b-q5_1.txt
|
|
time ./bin/quantize ../models/13B/ggml-model-f16.bin ../models/13B/ggml-model-q8_0.bin q8_0 2>&1 | tee ../qnt-13b-q8_0.txt
|
|
|
|
#
|
|
# perplexity
|
|
#
|
|
|
|
# 7B
|
|
time ./bin/perplexity -m ../models/7B/ggml-model-f16.bin -f ./wiki.test.raw --no-mmap -t 12 2>&1 | tee ../ppl-7b-f16.txt
|
|
time ./bin/perplexity -m ../models/7B/ggml-model-q4_0.bin -f ./wiki.test.raw --no-mmap -t 12 2>&1 | tee ../ppl-7b-q4_0.txt
|
|
time ./bin/perplexity -m ../models/7B/ggml-model-q4_1.bin -f ./wiki.test.raw --no-mmap -t 12 2>&1 | tee ../ppl-7b-q4_1.txt
|
|
time ./bin/perplexity -m ../models/7B/ggml-model-q5_0.bin -f ./wiki.test.raw --no-mmap -t 12 2>&1 | tee ../ppl-7b-q5_0.txt
|
|
time ./bin/perplexity -m ../models/7B/ggml-model-q5_1.bin -f ./wiki.test.raw --no-mmap -t 12 2>&1 | tee ../ppl-7b-q5_1.txt
|
|
time ./bin/perplexity -m ../models/7B/ggml-model-q8_0.bin -f ./wiki.test.raw --no-mmap -t 12 2>&1 | tee ../ppl-7b-q8_0.txt
|
|
|
|
# 13B
|
|
time ./bin/perplexity -m ../models/13B/ggml-model-f16.bin -f ./wiki.test.raw --no-mmap -t 12 2>&1 | tee ../ppl-13b-f16.txt
|
|
time ./bin/perplexity -m ../models/13B/ggml-model-q4_0.bin -f ./wiki.test.raw --no-mmap -t 12 2>&1 | tee ../ppl-13b-q4_0.txt
|
|
time ./bin/perplexity -m ../models/13B/ggml-model-q4_1.bin -f ./wiki.test.raw --no-mmap -t 12 2>&1 | tee ../ppl-13b-q4_1.txt
|
|
time ./bin/perplexity -m ../models/13B/ggml-model-q5_0.bin -f ./wiki.test.raw --no-mmap -t 12 2>&1 | tee ../ppl-13b-q5_0.txt
|
|
time ./bin/perplexity -m ../models/13B/ggml-model-q5_1.bin -f ./wiki.test.raw --no-mmap -t 12 2>&1 | tee ../ppl-13b-q5_1.txt
|
|
time ./bin/perplexity -m ../models/13B/ggml-model-q8_0.bin -f ./wiki.test.raw --no-mmap -t 12 2>&1 | tee ../ppl-13b-q8_0.txt
|