metadata
license: apache-2.0
inference: false
SLIM-QA-GEN-PHI-3
slim-qa-gen-phi-3 implements a specialized function-calling question and answer generation from a context passage, with output in the form of a python dictionary, e.g.,
`{'question': ['What were earnings per share in the most recent quarter?'], 'answer': ['$2.39'] }
This model is finetuned on top of phi-3-mini-4k-instruct base.
For fast inference use, we would recommend the 'quantized tool' version, e.g., 'slim-qa-gen-phi-3-tool'.
Prompt format:
function = "generate"params = "{'question, answer', 'boolean', or 'multiple choice'}"prompt = "<human> " + {text} + "\n" +
"<{function}> " + {params} + "</{function}>" + "\n<bot>:"
Transformers Script
model = AutoModelForCausalLM.from_pretrained("llmware/slim-qa-gen-phi-3")
tokenizer = AutoTokenizer.from_pretrained("llmware/slim-qa-gen-phi-3")
function = "generate"
params = "boolean"
text = "Tesla stock declined yesterday 8% in premarket trading after a poorly-received event in San Francisco yesterday, in which the company indicated a likely shortfall in revenue."
prompt = "<human>: " + text + "\n" + f"<{function}> {params} </{function}>\n<bot>:"
inputs = tokenizer(prompt, return_tensors="pt")
start_of_input = len(inputs.input_ids[0])
outputs = model.generate(
inputs.input_ids.to('cpu'),
eos_token_id=tokenizer.eos_token_id,
pad_token_id=tokenizer.eos_token_id,
do_sample=True,
temperature=0.7,
max_new_tokens=200
)
output_only = tokenizer.decode(outputs[0][start_of_input:], skip_special_tokens=True)
print("output only: ", output_only)
[OUTPUT]: {'llm_response': {'question': ['Did Telsa stock decline more than 5% yesterday?'], 'answer':['yes'] } }
# here's the fun part
try:
output_only = ast.literal_eval(llm_string_output)
print("success - converted to python dictionary automatically")
except:
print("fail - could not convert to python dictionary automatically - ", llm_string_output)
Using as Function Call in LLMWare
from llmware.models import ModelCatalog
slim_model = ModelCatalog().load_model("llmware/slim-qa-gen-phi-3", sample=True, temperature=0.5)
response = slim_model.function_call(text,params=["boolean"], function="generate")
print("llmware - llm_response: ", response)
Model Card Contact
Darren Oberst & llmware team