-
Notifications
You must be signed in to change notification settings - Fork 23
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
old results were just the mean, so need to be multiplied to give correct output
- Loading branch information
1 parent
07bff66
commit 9a7d2b5
Showing
32 changed files
with
592 additions
and
582 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,4 +1,4 @@ | ||
Size vs accuracy Pearson correlation: 0.22253111740340267 | ||
Size vs accuracy Pearson correlation p-value: 1.0851737884181684e-08 | ||
Quantisation vs accuracy Pearson correlation: 0.24295283470580717 | ||
Quantisation vs accuracy Pearson correlation p-value: 3.923401309641152e-10 | ||
Size vs accuracy Pearson correlation: 0.17210401537258263 | ||
Size vs accuracy Pearson correlation p-value: 1.0891261530140134e-05 | ||
Quantisation vs accuracy Pearson correlation: 0.20302475924649943 | ||
Quantisation vs accuracy Pearson correlation p-value: 1.9453161287669737e-07 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
116 changes: 58 additions & 58 deletions
116
benchmark/results/processed/explicit_relevance_of_single_fragments.csv
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
122 changes: 61 additions & 61 deletions
122
benchmark/results/processed/implicit_relevance_of_multiple_fragments.csv
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,63 +1,63 @@ | ||
Full model name,Score achieved,Score possible,Score SD,Accuracy,Iterations | ||
chatglm3:6:ggmlv3:q4_0,2.0,10.0,0,0.2,5 | ||
mistral-instruct-v0.2:7:ggufv2:Q3_K_M,2.0,10.0,0,0.2,5 | ||
llama-2-chat:70:ggufv2:Q4_K_M,2.0,10.0,0,0.2,5 | ||
llama-2-chat:7:ggufv2:Q2_K,2.0,10.0,0,0.2,5 | ||
llama-2-chat:7:ggufv2:Q3_K_M,2.0,10.0,0,0.2,5 | ||
llama-3-instruct:8:ggufv2:Q4_K_M,2.0,10.0,0,0.2,5 | ||
llama-3-instruct:8:ggufv2:Q5_K_M,2.0,10.0,0,0.2,5 | ||
llama-3-instruct:8:ggufv2:Q6_K,2.0,10.0,0,0.2,5 | ||
llama-3-instruct:8:ggufv2:Q8_0,2.0,10.0,0,0.2,5 | ||
mistral-instruct-v0.2:7:ggufv2:Q4_K_M,2.0,10.0,0,0.2,5 | ||
gpt-3.5-turbo-0613,2.0,10.0,0,0.2,5 | ||
mistral-instruct-v0.2:7:ggufv2:Q5_K_M,2.0,10.0,0,0.2,5 | ||
mistral-instruct-v0.2:7:ggufv2:Q6_K,2.0,10.0,0,0.2,5 | ||
mixtral-instruct-v0.1:46_7:ggufv2:Q4_K_M,2.0,10.0,0,0.2,5 | ||
mixtral-instruct-v0.1:46_7:ggufv2:Q5_K_M,2.0,10.0,0,0.2,5 | ||
openhermes-2.5:7:ggufv2:Q4_K_M,2.0,10.0,0,0.2,5 | ||
openhermes-2.5:7:ggufv2:Q5_K_M,2.0,10.0,0,0.2,5 | ||
openhermes-2.5:7:ggufv2:Q6_K,2.0,10.0,0,0.2,5 | ||
gpt-4-0613,2.0,10.0,0,0.2,5 | ||
openhermes-2.5:7:ggufv2:Q8_0,2.0,10.0,0,0.2,5 | ||
code-llama-instruct:34:ggufv2:Q2_K,2.0,10.0,0,0.2,5 | ||
code-llama-instruct:34:ggufv2:Q5_K_M,2.0,10.0,0,0.2,5 | ||
code-llama-instruct:7:ggufv2:Q4_K_M,2.0,10.0,0,0.2,5 | ||
gpt-3.5-turbo-0125,1.8,10.0,0,0.18,5 | ||
code-llama-instruct:7:ggufv2:Q6_K,1.8,10.0,0,0.18,5 | ||
mistral-instruct-v0.2:7:ggufv2:Q8_0,1.8,10.0,0,0.18,5 | ||
code-llama-instruct:34:ggufv2:Q6_K,1.8,10.0,0,0.18,5 | ||
code-llama-instruct:34:ggufv2:Q8_0,1.8,10.0,0,0.18,5 | ||
llama-2-chat:70:ggufv2:Q5_K_M,1.8,10.0,0,0.18,5 | ||
mixtral-instruct-v0.1:46_7:ggufv2:Q6_K,1.4,10.0,0,0.13999999999999999,5 | ||
code-llama-instruct:7:ggufv2:Q3_K_M,1.4,10.0,0,0.13999999999999999,5 | ||
code-llama-instruct:7:ggufv2:Q2_K,1.4,10.0,0,0.13999999999999999,5 | ||
gpt-4o-2024-05-13,1.4,10.0,0,0.13999999999999999,5 | ||
llama-2-chat:7:ggufv2:Q5_K_M,1.2,10.0,0,0.12,5 | ||
mixtral-instruct-v0.1:46_7:ggufv2:Q8_0,1.2,10.0,0,0.12,5 | ||
mixtral-instruct-v0.1:46_7:ggufv2:Q2_K,1.2,10.0,0,0.12,5 | ||
code-llama-instruct:34:ggufv2:Q3_K_M,1.0,10.0,0,0.1,5 | ||
llama-2-chat:70:ggufv2:Q2_K,1.0,10.0,0,0.1,5 | ||
code-llama-instruct:13:ggufv2:Q4_K_M,1.0,10.0,0,0.1,5 | ||
code-llama-instruct:13:ggufv2:Q5_K_M,1.0,10.0,0,0.1,5 | ||
openhermes-2.5:7:ggufv2:Q3_K_M,1.0,10.0,0,0.1,5 | ||
openhermes-2.5:7:ggufv2:Q2_K,1.0,10.0,0,0.1,5 | ||
code-llama-instruct:7:ggufv2:Q8_0,1.0,10.0,0,0.1,5 | ||
code-llama-instruct:13:ggufv2:Q6_K,1.0,10.0,0,0.1,5 | ||
code-llama-instruct:13:ggufv2:Q8_0,1.0,10.0,0,0.1,5 | ||
mixtral-instruct-v0.1:46_7:ggufv2:Q3_K_M,1.0,10.0,0,0.1,5 | ||
llama-2-chat:13:ggufv2:Q2_K,1.0,10.0,0,0.1,5 | ||
llama-2-chat:70:ggufv2:Q3_K_M,1.0,10.0,0,0.1,5 | ||
llama-2-chat:13:ggufv2:Q3_K_M,1.0,10.0,0,0.1,5 | ||
mistral-instruct-v0.2:7:ggufv2:Q2_K,1.0,10.0,0,0.1,5 | ||
llama-2-chat:13:ggufv2:Q4_K_M,1.0,10.0,0,0.1,5 | ||
llama-2-chat:13:ggufv2:Q5_K_M,1.0,10.0,0,0.1,5 | ||
gpt-4-0125-preview,1.0,10.0,0,0.1,5 | ||
llama-2-chat:13:ggufv2:Q6_K,1.0,10.0,0,0.1,5 | ||
llama-2-chat:7:ggufv2:Q8_0,1.0,10.0,0,0.1,5 | ||
llama-2-chat:7:ggufv2:Q6_K,1.0,10.0,0,0.1,5 | ||
llama-2-chat:7:ggufv2:Q4_K_M,1.0,10.0,0,0.1,5 | ||
llama-2-chat:13:ggufv2:Q8_0,1.0,10.0,0,0.1,5 | ||
code-llama-instruct:7:ggufv2:Q5_K_M,1.0,10.0,0,0.1,5 | ||
code-llama-instruct:34:ggufv2:Q4_K_M,0.8,10.0,0,0.08,5 | ||
code-llama-instruct:13:ggufv2:Q2_K,0.8,10.0,0,0.08,5 | ||
chatglm3:6:ggmlv3:q4_0,10.0,10.0,0,1.0,5 | ||
mistral-instruct-v0.2:7:ggufv2:Q3_K_M,10.0,10.0,0,1.0,5 | ||
llama-2-chat:70:ggufv2:Q4_K_M,10.0,10.0,0,1.0,5 | ||
llama-2-chat:7:ggufv2:Q2_K,10.0,10.0,0,1.0,5 | ||
llama-2-chat:7:ggufv2:Q3_K_M,10.0,10.0,0,1.0,5 | ||
llama-3-instruct:8:ggufv2:Q4_K_M,10.0,10.0,0,1.0,5 | ||
llama-3-instruct:8:ggufv2:Q5_K_M,10.0,10.0,0,1.0,5 | ||
llama-3-instruct:8:ggufv2:Q6_K,10.0,10.0,0,1.0,5 | ||
llama-3-instruct:8:ggufv2:Q8_0,10.0,10.0,0,1.0,5 | ||
mistral-instruct-v0.2:7:ggufv2:Q4_K_M,10.0,10.0,0,1.0,5 | ||
gpt-3.5-turbo-0613,10.0,10.0,0,1.0,5 | ||
mistral-instruct-v0.2:7:ggufv2:Q5_K_M,10.0,10.0,0,1.0,5 | ||
mistral-instruct-v0.2:7:ggufv2:Q6_K,10.0,10.0,0,1.0,5 | ||
mixtral-instruct-v0.1:46_7:ggufv2:Q4_K_M,10.0,10.0,0,1.0,5 | ||
mixtral-instruct-v0.1:46_7:ggufv2:Q5_K_M,10.0,10.0,0,1.0,5 | ||
openhermes-2.5:7:ggufv2:Q4_K_M,10.0,10.0,0,1.0,5 | ||
openhermes-2.5:7:ggufv2:Q5_K_M,10.0,10.0,0,1.0,5 | ||
openhermes-2.5:7:ggufv2:Q6_K,10.0,10.0,0,1.0,5 | ||
gpt-4-0613,10.0,10.0,0,1.0,5 | ||
openhermes-2.5:7:ggufv2:Q8_0,10.0,10.0,0,1.0,5 | ||
code-llama-instruct:34:ggufv2:Q2_K,10.0,10.0,0,1.0,5 | ||
code-llama-instruct:34:ggufv2:Q5_K_M,10.0,10.0,0,1.0,5 | ||
code-llama-instruct:7:ggufv2:Q4_K_M,10.0,10.0,0,1.0,5 | ||
gpt-3.5-turbo-0125,9.0,10.0,0,0.9,5 | ||
code-llama-instruct:7:ggufv2:Q6_K,9.0,10.0,0,0.9,5 | ||
mistral-instruct-v0.2:7:ggufv2:Q8_0,9.0,10.0,0,0.9,5 | ||
code-llama-instruct:34:ggufv2:Q6_K,9.0,10.0,0,0.9,5 | ||
code-llama-instruct:34:ggufv2:Q8_0,9.0,10.0,0,0.9,5 | ||
llama-2-chat:70:ggufv2:Q5_K_M,9.0,10.0,0,0.9,5 | ||
mixtral-instruct-v0.1:46_7:ggufv2:Q6_K,7.0,10.0,0,0.7,5 | ||
code-llama-instruct:7:ggufv2:Q3_K_M,7.0,10.0,0,0.7,5 | ||
code-llama-instruct:7:ggufv2:Q2_K,7.0,10.0,0,0.7,5 | ||
gpt-4o-2024-05-13,7.0,10.0,0,0.7,5 | ||
llama-2-chat:7:ggufv2:Q5_K_M,6.0,10.0,0,0.6,5 | ||
mixtral-instruct-v0.1:46_7:ggufv2:Q8_0,6.0,10.0,0,0.6,5 | ||
mixtral-instruct-v0.1:46_7:ggufv2:Q2_K,6.0,10.0,0,0.6,5 | ||
code-llama-instruct:34:ggufv2:Q3_K_M,5.0,10.0,0,0.5,5 | ||
llama-2-chat:70:ggufv2:Q2_K,5.0,10.0,0,0.5,5 | ||
code-llama-instruct:13:ggufv2:Q4_K_M,5.0,10.0,0,0.5,5 | ||
code-llama-instruct:13:ggufv2:Q5_K_M,5.0,10.0,0,0.5,5 | ||
openhermes-2.5:7:ggufv2:Q3_K_M,5.0,10.0,0,0.5,5 | ||
openhermes-2.5:7:ggufv2:Q2_K,5.0,10.0,0,0.5,5 | ||
code-llama-instruct:7:ggufv2:Q8_0,5.0,10.0,0,0.5,5 | ||
code-llama-instruct:13:ggufv2:Q6_K,5.0,10.0,0,0.5,5 | ||
code-llama-instruct:13:ggufv2:Q8_0,5.0,10.0,0,0.5,5 | ||
mixtral-instruct-v0.1:46_7:ggufv2:Q3_K_M,5.0,10.0,0,0.5,5 | ||
llama-2-chat:13:ggufv2:Q2_K,5.0,10.0,0,0.5,5 | ||
llama-2-chat:70:ggufv2:Q3_K_M,5.0,10.0,0,0.5,5 | ||
llama-2-chat:13:ggufv2:Q3_K_M,5.0,10.0,0,0.5,5 | ||
mistral-instruct-v0.2:7:ggufv2:Q2_K,5.0,10.0,0,0.5,5 | ||
llama-2-chat:13:ggufv2:Q4_K_M,5.0,10.0,0,0.5,5 | ||
llama-2-chat:13:ggufv2:Q5_K_M,5.0,10.0,0,0.5,5 | ||
gpt-4-0125-preview,5.0,10.0,0,0.5,5 | ||
llama-2-chat:13:ggufv2:Q6_K,5.0,10.0,0,0.5,5 | ||
llama-2-chat:7:ggufv2:Q8_0,5.0,10.0,0,0.5,5 | ||
llama-2-chat:7:ggufv2:Q6_K,5.0,10.0,0,0.5,5 | ||
llama-2-chat:7:ggufv2:Q4_K_M,5.0,10.0,0,0.5,5 | ||
llama-2-chat:13:ggufv2:Q8_0,5.0,10.0,0,0.5,5 | ||
code-llama-instruct:7:ggufv2:Q5_K_M,5.0,10.0,0,0.5,5 | ||
code-llama-instruct:34:ggufv2:Q4_K_M,4.0,10.0,0,0.4,5 | ||
code-llama-instruct:13:ggufv2:Q2_K,4.0,10.0,0,0.4,5 | ||
code-llama-instruct:13:ggufv2:Q3_K_M,0.0,10.0,0,0.0,5 |
Oops, something went wrong.