---
license: cc-by-nc-sa-4.0
datasets:
- ed001/ds-coder-instruct-v1
language:
- en
pipeline_tag: text-generation
tags:
- code
- data science
---
# The Data Science Coder
Data Science coder is a group of fine tuned models designed to help with coding for data science applications. It comes in 2 variants: 1.3b and 6.7b. Models are fine tuned from DeepSeek Coder instruct versions. Fine tuning was performed on the [ed001/ds-coder-instruct-v1](https://huggingface.co/datasets/ed001/ds-coder-instruct-v1) dataset which is constructed by filtering publicly available datasets on HuggingFace.
## Usage
```python
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
def build_instruction_prompt(instruction):
return '''
You are the Data Science Coder, a helpful AI assistant created by a man named Ed.
You help people with data science coding and you answer questions about data science in a helpful manner.
### Instruction:
{}
### Response:
'''.format(instruction.strip()).lstrip()
tokenizer = AutoTokenizer.from_pretrained("ed001/datascience-coder-1.3b", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("ed001/datascience-coder-1.3b", trust_remote_code=True).cuda()
pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=1024, top_p=0.95)
result = pipe(build_instruction_prompt("Perform EDA on the Iris dataset"))
print(result[0]['generated_text'])
```
## Training Details
lora_r: 16
lora_alpha: 8
lora_dropout: 0.05
target_modules: q, k, v, o, gate_proj, down_proj, up_proj, lm_head
weight_decay: 0
optmizer: paged_adamw_32bit
lr: 1e-4
lr_scheduler: cosine
max_seq_len: 4096
batch_size: 4
max_grad_norm: 0.5
warmup_ratio: 0.05
num_epochs: 1
Training was performed on the python subset of the ds-coder-instruct dataset.
## Examples
## Contact
GitHub: [Ea0011](https://github.com/Ea0011)