issues
search
Psycoy
/
MixEval
The official evaluation suite and dynamic data release for MixEval.
https://mixeval.github.io/
178
stars
24
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Problem in Inference of Local Chat Model
#23
carstendraschner
closed
1 day ago
1
Padding Handling for Local Chat
#22
carstendraschner
closed
1 day ago
0
Handling default Padding Token and offer System Prompt
#21
carstendraschner
closed
6 days ago
0
Weird random answer if API endpoint is not available
#20
carstendraschner
closed
1 week ago
3
Default Local Chat Tokenizer Padding Side "left" for multi batch inference
#19
carstendraschner
closed
2 weeks ago
2
Make System Prompt Arg Available for Local Chat Model Evaluation
#18
carstendraschner
closed
6 days ago
0
(Non) Reproducible Experiment Results
#17
carstendraschner
closed
2 weeks ago
3
Azure Open AI API support within Judge
#16
carstendraschner
closed
2 weeks ago
0
Examples for open-source model judges & parsers
#15
IdoGalilDeci
closed
2 weeks ago
6
[RFC] Local models, remote install and more losely dependencies
#14
philschmid
opened
3 weeks ago
2
Question about the paper
#13
felipemaiapolo
closed
3 weeks ago
1
Support for Azure OpenAI API?
#12
Ignoramus0817
closed
3 weeks ago
2
Create __init__.py to load mix_eval as package [WIP]
#11
Whadup
opened
1 month ago
2
Duplicates in benchmark data
#10
carstendraschner
closed
1 month ago
3
Are the evaluation data from different benchmarks available?
#9
felipemaiapolo
closed
1 month ago
1
The answer set here is a 100% wrong.
#8
XapaJIaMnu-at-meta
closed
1 month ago
1
audio-in
#7
qiantong-xu
closed
2 weeks ago
0
Add tqdm progress bar when doing batched inference for evaluations
#6
teknium1
closed
1 month ago
1
Requesting new models?
#5
jtsorlinis
closed
1 month ago
1
Default SYSTEM_MESSAGE for Llama 3 Instruct is "You are a pirate chatbot who always responds in pirate speak!"
#4
lhl
closed
1 month ago
1
Adding qwen-2-7B-instruct
#3
RodriMora
closed
1 month ago
1
CUDA out of memory error
#2
RodriMora
closed
1 month ago
5
Can GGUF and EXL2 compatibility be added?
#1
RodriMora
closed
1 month ago
8