|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- ekshat/text-2-sql-with-context |
|
language: |
|
- en |
|
--- |
|
--- |
|
datasets: |
|
- ekshat/text-2-sql-with-context |
|
language: |
|
- en |
|
library_name: transformers |
|
pipeline_tag: text-generation |
|
tags: |
|
- text-2-sql |
|
- text-generation |
|
- text2sql |
|
|
|
# Inference |
|
```python |
|
!pip install transformers accelerate xformers bitsandbytes |
|
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("ekshat/Llama-2-7b-chat-finetune-for-text2sql") |
|
|
|
# Loading model in 4 bit precision |
|
model = AutoModelForCausalLM.from_pretrained("ekshat/Llama-2-7b-chat-finetune-for-text2sql", load_in_4bit=True) |
|
|
|
context = "CREATE TABLE head (name VARCHAR, born_state VARCHAR, age VARCHAR)" |
|
question = "List the name, born state and age of the heads of departments ordered by age." |
|
|
|
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:""" |
|
|
|
pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200) |
|
result = pipe(prompt) |
|
print(result[0]['generated_text']) |
|
``` |
|
|
|
|
|
# Model Information |
|
- **model_name = "NousResearch/Llama-2-7b-chat-hf"** |
|
|
|
- **dataset_name = "ekshat/text-2-sql-with-context"** |
|
|
|
|
|
# QLoRA parameters |
|
- **lora_r = 64** |
|
|
|
- **lora_alpha = 16** |
|
|
|
- **lora_dropout = 0.1** |
|
|
|
|
|
# BitsAndBytes parameters |
|
- **use_4bit = True** |
|
|
|
- **bnb_4bit_compute_dtype = "float16"** |
|
|
|
- **bnb_4bit_quant_type = "nf4"** |
|
|
|
- **use_nested_quant = False** |
|
|
|
|
|
# Training Arguments parameters |
|
- **num_train_epochs = 1** |
|
|
|
- **fp16 = False** |
|
|
|
- **bf16 = False** |
|
|
|
- **per_device_train_batch_size = 8** |
|
|
|
- **per_device_eval_batch_size = 4** |
|
|
|
- **gradient_accumulation_steps = 1** |
|
|
|
- **gradient_checkpointing = True** |
|
|
|
- **max_grad_norm = 0.3** |
|
|
|
- **learning_rate = 2e-4** |
|
|
|
- **weight_decay = 0.001** |
|
|
|
- **optim = "paged_adamw_32bit"** |
|
|
|
- **lr_scheduler_type = "cosine"** |
|
|
|
- **max_steps = -1** |
|
|
|
- **warmup_ratio = 0.03** |
|
|
|
- **group_by_length = True** |
|
|
|
- **save_steps = 0** |
|
|
|
- **logging_steps = 25** |
|
|
|
|
|
# SFT parameters |
|
- **max_seq_length = None** |
|
|
|
- **packing = False** |
