File size: 1,951 Bytes
1ec4534 2bb1c6e 2aac15e ce093c5 2f85623 a88a0ac 3d0a338 e829b11 c3f5f91 c80ce94 c3f5f91 c80ce94 c3f5f91 01beac2 c80ce94 c3f5f91 c80ce94 c3f5f91 a88a0ac 208309c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 |
---
language:
- th
- en
license: mit
base_model: aisingapore/sea-lion-7b-instruct
datasets:
- AIAT/Optimizer-datasetfinal
pipeline_tag: text-generation
---
## Sea-lion2pandas
fine-tuned from [sea-lion-7b-instruct](aisingapore/sea-lion-7b-instruct) with question-pandas expression pairs.
## How to use:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import pandas as pd
tokenizer = AutoTokenizer.from_pretrained("AIAT/Optimizer-sealion2pandas", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("AIAT/Optimizer-sealion2pandas", trust_remote_code=True)
df = pd.read_csv("Your csv..")
prompt_template = "### USER:\n{human_prompt}\n\n### RESPONSE:\n"
prompt = """\
You are working with a pandas dataframe in Python.
The name of the dataframe is `df`.
This is the result of `print(df.head())`:
{df_str}
Follow these instructions:
1. Convert the query to executable Python code using Pandas.
2. The final line of code should be a Python expression that can be called with the `eval()` function.
3. The code should represent a solution to the query.
4. PRINT ONLY THE EXPRESSION.
5. Do not quote the expression.
Query: {query_str} """
def create_prompt(query_str, df):
text = prompt.format(df_str=str(df.head()), query_str=query_str)
text = prompt_template.format(human_prompt=text)
return text
full_prompt = create_prompt("Find test ?", df)
tokens = tokenizer(full_prompt, return_tensors="pt")
output = model.generate(tokens["input_ids"], max_new_tokens=20, eos_token_id=tokenizer.eos_token_id)
print(tokenizer.decode(output[0], skip_special_tokens=True))
```
# sponser
 |