jiebi commited on
Commit
e999efe
·
verified ·
1 Parent(s): bd34731

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +36 -1
README.md CHANGED
@@ -9,4 +9,39 @@ base_model:
9
  pipeline_tag: feature-extraction
10
  tags:
11
  - retrieval
12
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  pipeline_tag: feature-extraction
10
  tags:
11
  - retrieval
12
+ ---
13
+
14
+
15
+ # Model Card for Model ID
16
+
17
+ <!-- Provide a quick summary of what the model is/does. -->
18
+
19
+ IDs-C2I-Enc is a bi-encoder retrieval model specifically fine-tuned for the IDs subset of the CodeConvo dataset. (IDs is short for Internet-Drafts)
20
+
21
+ - **Paper:** [Automated Insights Into GitHub Collaboration Dynamics](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10982058)
22
+ - **Training Dataset:** [jiebi/CodeConvo](https://huggingface.co/datasets/jiebi/CodeConvo)
23
+
24
+ ## Uses
25
+
26
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
27
+
28
+ You can use MTEB to load this model ([source code](https://github.com/cheop-byeon/mteb-R2Gen/blob/main/mteb/models/bge_models.py)).
29
+
30
+ To run the IR evaluation task ([source code](https://github.com/cheop-byeon/mteb-R2Gen/blob/main/RFCAlign_IR_mteb.py)).
31
+
32
+ ## Training Details
33
+
34
+ You can reproduce this with [this script](https://github.com/cheop-byeon/FlagEmbedding/blob/main/examples/finetune/embedder/encoder_only/ft_CodeConvo_encoder.sh) (reproduced here for convenience).
35
+
36
+ ## Citation
37
+
38
+ ```bibtex
39
+ @article{bian2025automated,
40
+ title={Automated Insights Into GitHub Collaboration Dynamics},
41
+ author={Bian, Jie and Arefev, Nikolay and M{\"u}hlh{\"a}user, Max and Welzl, Michael},
42
+ journal={IEEE Access},
43
+ volume={13},
44
+ pages={85526--85542},
45
+ year={2025}
46
+ }
47
+ ```