metadata
base_model: unsloth/phi-3-mini-4k-instruct-bnb-4bit
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
Uploaded model
- Developed by: Majipa
- License: apache-2.0
- Finetuned from model : unsloth/phi-3-mini-4k-instruct-bnb-4bit
This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.
Using the model
from transformers import AutoModelForCausalLM, BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(load_in_4bit=True)
model = AutoModelForCausalLM.from_pretrained("Majipa/text-to-SQL",
device_map="cuda",
torch_dtype="auto",
quantization_config=quantization_config)
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
messages = [
{"role": "system", "content": "You are a helpful text-to-SQL assistant."},
{"role": "user", "content": "question: How many heads of the departments are older than 56 ? context: CREATE TABLE head (age INTEGER)"},
]
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
)
generation_args = {
"max_new_tokens": 500,
"temperature": 0.7,
}
output = pipe(messages, **generation_args)
print(output[0]['generated_text'])