README.md

---
license: cc-by-nc-4.0
base_model: bigcode/starcoder2-7b
language:
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- code
- starcoder
- bigcode
- sft
- 7b
---
# Starcoder-2-chat

![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64fc6d81d75293f417fee1d1/wBG0LiRCyd84baFneNgpg.jpeg)



<!-- Provide a quick summary of what the model is/does. -->
Starcoder-2-chat is an instruction fine-tuned of [bigcode/starcoder2-7b](https://huggingface.co/bigcode/starcoder2-7b) using the [glaiveai/glaive-code-assistant-v2](https://huggingface.co/datasets/glaiveai/glaive-code-assistant-v2) dataset using LoRA.


## 🏆 Evaluation results

Thanks to [Muhammad Bin Usman](https://www.linkedin.com/in/muhammad-bin-usman/) for running evals on Starcoder2-chat.

### HUMANEVAL
    0.3231707317073171
    
### HUMANEVALPLUS
    0.25609756097560976

### INSTRUCT-HUMANEVAL
    0.3231707317073171

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-7
- train_batch_size: 2
- eval_batch_size: Not specified
- seed: Not specified
- gradient_accumulation_steps: 8
- total_train_batch_size: Not specified
- optimizer: PagedAdamW with 32-bit precision
- lr_scheduler_type: Cosine
- lr_scheduler_warmup_steps: 100
- training_epoch: 1


### Framework versions

- Transformers 4.39.0.dev0
- Peft 0.9.1.dev0
- Datasets 2.18.0
- torch 2.2.0
- accelerate 0.27.2