wassname/Judgemark-v2lp
1
0
Fork 0
mirror of https://github.com/wassname/Judgemark-v2lp.git synced 2026-08-11 11:12:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

res

Browse Source
This commit is contained in:
wassname
2025-07-26 12:47:17 +08:00
parent 3c7e7d58b7
commit c0f72bcdb3
2 changed files with 174 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+6 -7
View File
@@ -13,14 +13,13 @@ This project compares different methods of extracting scores from language model
## Results
| Method | Score | Score (Normalized) |
| Method | Score | Score (Normalized) |
|---------------|----------|------------|
| ranked_scaled | 0.629332 | 0.80 |
| ranked_norm | 0.654562 | 0.74 |
| weighted | 0.634804 | 0.65 |
| raw | 0.634528 | 0.65 |
| weighted_norm | 0.623806 | 0.64 |
| ranked | 0.336333 | 0.28 |
| ranked_scaled | 0.62 | 0.80 |
| ranked_norm | 0.65 | 0.74 |
| weighted | 0.63 | 0.65 |
| raw (baseline)| 0.63 | 0.65 |
| weighted_norm | 0.62 | 0.64 |
*Results for DeepSeek Chat V3 0324*
nbs/02_recomp.ipynb
+168
View File
@@ -1238,6 +1238,174 @@
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "15176e01aad14ebfbd291c777f801d35",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/24 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "0ca2e8e583fb4a118381603970645368",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/5 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "433bdf6c0fa54171a006cb932039ec54",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/24 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "0f1f34503e254338b3ab9570c8ca5a4f",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/24 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "373260d7f9da45a79f4795c00d256a99",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/24 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "8e9982f3087c42afafaf6fa19117cd56",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/24 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "50b76e35c3484083a6c2faae639176a7",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/24 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "19d64d9e00c245a7bc8cdf778697a370",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/5 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "2681abb232e84334a414cea988541b82",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/24 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "b9232558182d476a9b0662e1353642d2",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/24 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "f2362dba5f38439a9243dc9f26c90ce7",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/24 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "4485b8426297439295e8a4f39de30296",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/24 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [