Update README.md
Browse files
README.md
CHANGED
|
@@ -16,9 +16,14 @@ ModularStarEncoder-finetuned-4 is an encoder built on top of [ModularStarEncoder
|
|
| 16 |
ModularStarEncoder fine-tuned-4 is an encoder for various retrieval tasks, enabling the end user to select the model size that meets their memory and computational constraints.
|
| 17 |
We built ModularStarEncoder on top of [StarCoder-2](https://huggingface.co/bigcode/starcoder2-15b), reducing its size from 15B to 1B parameters in bfloat16.
|
| 18 |
This version contains only the first 4 layers of ModularStarEncoder-finetuned, with the related projection head.
|
|
|
|
| 19 |
We have released this version to enhance the model's usability by allowing users to download only the desired size.
|
|
|
|
| 20 |
The model is finetuned with [CLIP objective](https://github.com/mlfoundations/open_clip/blob/main/src/open_clip/loss.py)
|
| 21 |
|
|
|
|
|
|
|
|
|
|
| 22 |
- **Paper:** [Link](arxiv.paper)
|
| 23 |
- **Languages:** English, Go, Ruby, Python, Java, C++, PHP, C, JavaScript
|
| 24 |
|
|
|
|
| 16 |
ModularStarEncoder fine-tuned-4 is an encoder for various retrieval tasks, enabling the end user to select the model size that meets their memory and computational constraints.
|
| 17 |
We built ModularStarEncoder on top of [StarCoder-2](https://huggingface.co/bigcode/starcoder2-15b), reducing its size from 15B to 1B parameters in bfloat16.
|
| 18 |
This version contains only the first 4 layers of ModularStarEncoder-finetuned, with the related projection head.
|
| 19 |
+
|
| 20 |
We have released this version to enhance the model's usability by allowing users to download only the desired size.
|
| 21 |
+
|
| 22 |
The model is finetuned with [CLIP objective](https://github.com/mlfoundations/open_clip/blob/main/src/open_clip/loss.py)
|
| 23 |
|
| 24 |
+
ModularStarEncoder fine-tuned works with instruction prompts; to get the most out of the model, embed the task in the input. The How to Use section below provides more details.
|
| 25 |
+
|
| 26 |
+
|
| 27 |
- **Paper:** [Link](arxiv.paper)
|
| 28 |
- **Languages:** English, Go, Ruby, Python, Java, C++, PHP, C, JavaScript
|
| 29 |
|