Update README.md
Browse filesFill in model details
README.md
CHANGED
@@ -8,4 +8,33 @@ pipeline_tag: text-generation
|
|
8 |
tags:
|
9 |
- code
|
10 |
- data science
|
11 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
tags:
|
9 |
- code
|
10 |
- data science
|
11 |
+
---
|
12 |
+
|
13 |
+
# The Data Science Coder
|
14 |
+
|
15 |
+
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.
|
16 |
+
|
17 |
+
## Usage
|
18 |
+
|
19 |
+
```python
|
20 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
|
21 |
+
|
22 |
+
def build_instruction_prompt(instruction):
|
23 |
+
return '''
|
24 |
+
You are the Data Science Coder, a helpful AI assistant created by a man named Ed.
|
25 |
+
You help people with data science coding and you answer questions about data science in a helpful manner.
|
26 |
+
### Instruction:
|
27 |
+
{}
|
28 |
+
### Response:
|
29 |
+
'''.format(instruction.strip()).lstrip()
|
30 |
+
|
31 |
+
tokenizer = AutoTokenizer.from_pretrained("ed001/datascience-coder-6.7b", trust_remote_code=True)
|
32 |
+
model = AutoModelForCausalLM.from_pretrained("ed001/datascience-coder-6.7b", trust_remote_code=True).cuda()
|
33 |
+
pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=1024, top_p=0.95)
|
34 |
+
result = pipe(build_instruction_prompt("Perform EDA on the Iris dataset"))
|
35 |
+
print(result[0]['generated_text'])
|
36 |
+
|
37 |
+
```
|
38 |
+
|
39 |
+
## Contact
|
40 |
+
GitHub: [Ea0011](https://github.com/Ea0011)
|