This commit is contained in:
Paul Gauthier 2024-11-21 11:38:41 -08:00
parent a3dde4599a
commit 8448eff1eb
4 changed files with 113 additions and 6 deletions

View file

@ -0,0 +1,93 @@
- dirname: 2024-11-09-11-09-15--Qwen2.5-Coder-32B-Instruct
test_cases: 133
model: HuggingFace weights via glhf.chat
released: 2024-11-12
edit_format: diff
commit_hash: ec9982a
pass_rate_1: 59.4
pass_rate_2: 71.4
percent_cases_well_formed: 94.7
error_outputs: 17
num_malformed_responses: 17
num_with_malformed_responses: 7
user_asks: 1
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 3
command: aider --model openai/Qwen2.5-Coder-32B-Instruct
date: 2024-11-09
versions: 0.59.2.dev
seconds_per_case: 22.5
total_cost: 0.0000
- dirname: 2024-11-20-15-17-37--qwen25-32b-or-diff
test_cases: 133
model: openrouter/qwen/qwen-2.5-coder-32b-instruct
edit_format: diff
commit_hash: e917424
pass_rate_1: 49.6
pass_rate_2: 65.4
percent_cases_well_formed: 84.2
error_outputs: 43
num_malformed_responses: 31
num_with_malformed_responses: 21
user_asks: 43
lazy_comments: 0
syntax_errors: 2
indentation_errors: 2
exhausted_context_windows: 12
test_timeouts: 2
command: aider --model openrouter/qwen/qwen-2.5-coder-32b-instruct
date: 2024-11-20
versions: 0.63.3.dev
seconds_per_case: 40.7
total_cost: 0.1497
- dirname: 2024-09-20-21-47-17--qwen2.5-32b-instruct-q8_0-whole
test_cases: 133
model: ollama/qwen2.5:32b-instruct-q8_0
edit_format: whole
commit_hash: 2753ac6
pass_rate_1: 46.6
pass_rate_2: 58.6
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 1
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 2
command: aider --model ollama/qwen2.5:32b-instruct-q8_0
date: 2024-09-20
versions: 0.56.1.dev
seconds_per_case: 1763.7
total_cost: 0.0000
- dirname: 2024-09-30-14-09-43--qwen2.5-32b-whole-2
test_cases: 133
model: ollama/qwen2.5:32b
edit_format: whole
commit_hash: 765c4cb
pass_rate_1: 44.4
pass_rate_2: 54.1
percent_cases_well_formed: 100.0
error_outputs: 0
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 9
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 3
command: aider --model ollama/qwen2.5:32b
date: 2024-09-30
versions: 0.58.1.dev
seconds_per_case: 134.9
total_cost: 0.0000