modularStarEncoder
/

ModularStarEncoder-finetuned

Feature Extraction

ModularStarEncoder

Model card Files Files and versions Community

andreagurioli1995 commited on 11 days ago

Commit

4e674c0

·

verified ·

1 Parent(s): e1d2393

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -12,7 +12,7 @@ base_model:
 <!-- Provide a quick summary of what the model is/does. -->
-ModularStarEncoder-finetuned (MoSE) is an encoder built on top of [ModularStarEncoder-1B Pre-trained](https://huggingface.co/andreagurioli1995/ModularStarEncoder) on [SynthCode2Code2NL](https://huggingface.co/datasets/andreagurioli1995/SynthCode2Code2NL-neardedup).
 ModularStarEncoder, fine-tuned, is an encoder for code-to-code and text-to-code retrieval tasks, enabling the end user to select the model size that meets their memory and computational constraints.
 We built ModularStarEncoder on top of [StarCoder-2](https://huggingface.co/bigcode/starcoder2-15b), reducing its size from 15B to 1B parameters in bfloat16.

 <!-- Provide a quick summary of what the model is/does. -->
+ModularStarEncoder-finetuned (MoSE) is an encoder built on top of [ModularStarEncoder-1B Pre-trained](https://huggingface.co/andreagurioli1995/ModularStarEncoder) on [SynthCoNL](https://huggingface.co/datasets/andreagurioli1995/SynthCode2Code2NL-neardedup).
 ModularStarEncoder, fine-tuned, is an encoder for code-to-code and text-to-code retrieval tasks, enabling the end user to select the model size that meets their memory and computational constraints.
 We built ModularStarEncoder on top of [StarCoder-2](https://huggingface.co/bigcode/starcoder2-15b), reducing its size from 15B to 1B parameters in bfloat16.