|
--- |
|
datasets: |
|
- b-mc2/sql-create-context |
|
language: |
|
- en |
|
library_name: transformers |
|
pipeline_tag: text2text-generation |
|
tags: |
|
- text-2-sql |
|
- text-generation-inference |
|
--- |
|
This Model is based on Llama-2 7B model provided by Meta. The Model accepts text and return SQL-query. This Model has been fine-tuned on "NousResearch/Llama-2-7b-hf". |
|
|
|
```python |
|
! pip install transformers accelerate |
|
|
|
# Use a pipeline as a high-level helper |
|
from transformers import pipeline |
|
|
|
pipe = pipeline("text2text-generation", model="ekshat/Llama-2-7b-chat-finetune-for-text2sql") |
|
|
|
# Load model directly |
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("ekshat/Llama-2-7b-chat-finetune-for-text2sql") |
|
model = AutoModelForCausalLM.from_pretrained("ekshat/Llama-2-7b-chat-finetune-for-text2sql") |
|
|
|
# Run text generation pipeline with our model |
|
context = "CREATE TABLE Student (name VARCHAR, college VARCHAR, age VARCHAR, group VARCHAR, marks VARCHAR)" |
|
question = "List the name of Students belongs to school 'St. Xavier' and having marks greater than '600'" |
|
|
|
prompt = f"""Below is an context that describes a sql query, paired with an question that provides further information. Write an answer that appropriately completes the request. |
|
### Context: |
|
{context} |
|
### Question: |
|
{question} |
|
### Answer:""" |
|
|
|
sequences = pipeline( |
|
prompt, |
|
do_sample=True, |
|
top_k=10, |
|
num_return_sequences=1, |
|
eos_token_id=tokenizer.eos_token_id, |
|
max_length=200, |
|
) |
|
for seq in sequences: |
|
print(f"Result: {seq['generated_text']}") |
|
|
|
``` |