README.md

---
library_name: transformers
datasets:
- bigcode/the-stack-v2
license: bigcode-openrail-m
base_model:
- andreagurioli1995/ModularStarEncoder
---

# ModularStarEncoder-1B Fine-Tuned model

<!-- Provide a quick summary of what the model is/does. -->

ModularStarEncoder-finetuned is an encoder built on top of [ModularStarEncoder-1B Pre-trained](https://huggingface.co/andreagurioli1995/ModularStarEncoder) on [SynthCode2Code2NL](add link here). 
ModularStarEncoder fine-tuned is an encoder for various 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.

The model is finetuned with [CLIP objective](https://github.com/mlfoundations/open_clip/blob/main/src/open_clip/loss.py)

- **Paper:** [Link](arxiv.paper)
- **Languages:** English, Go, Ruby, Python, Java, C++, PHP, C, JavaScript

### How to use
```python
from transformers import AutoModel
from transformers import AutoTokenizer

#import the model
model = AutoModel.from_pretrained("andreagurioli1995/ModularStarEncoder-finetuned", trust_remote_code=True)

#import the tokenizer
tokenizer = AutoTokenizer.from_pretrained("andreagurioli1995/ModularStarEncoder-finetuned")

 
language = "yourlanguagelowercased"

#instruction in case of code embedding in a code language
instruction_code = f"Represent this {language} code snippet for retrieval:"

#instruction in case of code embedding in English
instruction_natural_language = "Represent this code description for retrieving supporting snippets of code:"

code_snippet = "your code to embed here"

#You should follow this pattern to embed a snippet of code or natural language queries 
sentence =  f"{tokenizer.sep_token}{instruction_code}{tokenizer.sep_token}{code_snippet)}{tokenizer.cls_token}"

#Tokenizing your sentence
tokenized_sensence = tokenizer(sentence, return_tensors="pt",truncation=True, max_length=2048)

#Embedding the tokenized sentence
embedded_sentence = model(**sentence)
```

You will get as an output three elements:

- projected_pooled_normalized: a list of the projected, pooled, and normalized embeddings from the five exit points;
- raw_hidden_states: raw representation from all the hidden states of the model, without pooling, normalization, and projection
- attentions: attention scores from the encoder
  
  
### Training

<!-- Provide a longer summary of what this model is. -->
We fine-tuned ModularStarEncoder with a batch size of 2048 contrastive samples for 20,000 training steps.
The pre-training and fine-tuning were conducted on 512 NVIDIA Ampere (64GB) GPUs using the [Leonardo](https://arxiv.org/abs/2307.16885) supercomputer, requiring 450,000 GPU working hours.

| Hyperparameter           | Value     |
|--------------------------|-----------|
| Hidden size              | 1024      |
| Max. position embeddings | 2048      |
| Num. of attention heads  | 12        |
| Num. of key values heads | 4         |
| Num. of hidden layers    | 36        |
| Attention                | GQA       |
| Num. of parameters       | ≈1B       |
|Loss function             |CLIP loss  |
|Multi-layer loss          | yes       |

## Licence 
The model is licensed under the BigCode OpenRAIL-M v1 license agreement. You can find the full agreement [here](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement).