root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-11-13 14:29:52 +00:00
Code Issues Actions 11 Packages Projects Releases Wiki Activity
f7276f7500
llama.cpp/examples/quantize
History
Kawrakow 66d575c45c
llama : add Q3_K_XS (#5060) 
* Add Q3_K_XS - intermediate size between Q2_K and Q3_K_S

* Q3_K_XS: quanize first 1/8 of ffn_down layers with Q4_K

Together with an importance matrix, this brings perplexity
for LLaMA-v2-70B below the perplexity of the former Q2_K
with a 800 MB smaller quantized model size.

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-01-22 12:43:33 +02:00
..
CMakeLists.txt build : link against build info instead of compiling against it (#3879) 2023-11-02 08:50:16 +02:00
quantize.cpp llama : add Q3_K_XS (#5060) 2024-01-22 12:43:33 +02:00
README.md readme : add some recent perplexity and bpw measurements to READMES, link for k-quants (#3340) 2023-09-27 18:30:36 +03:00

README.md

quantize

TODO

Llama 2 7B

Quantization Bits per Weight (BPW)
Q2_K 3.35
Q3_K_S 3.50
Q3_K_M 3.91
Q3_K_L 4.27
Q4_K_S 4.58
Q4_K_M 4.84
Q5_K_S 5.52
Q5_K_M 5.68
Q6_K 6.56

Llama 2 13B

Quantization Bits per Weight (BPW)
Q2_K 3.34
Q3_K_S 3.48
Q3_K_M 3.89
Q3_K_L 4.26
Q4_K_S 4.56
Q4_K_M 4.83
Q5_K_S 5.51
Q5_K_M 5.67
Q6_K 6.56

Llama 2 70B

Quantization Bits per Weight (BPW)
Q2_K 3.40
Q3_K_S 3.47
Q3_K_M 3.85
Q3_K_L 4.19
Q4_K_S 4.53
Q4_K_M 4.80
Q5_K_S 5.50
Q5_K_M 5.65
Q6_K 6.56