license: apache-2.0
inference: false
SLIM-RATINGS
slim-ratings is part of the SLIM ("Structured Language Instruction Model") model series, consisting of small, specialized decoder-based models, fine-tuned for function-calling.
slim-ratings has been fine-tuned for rating/stars (sentiment degree) function calls, generating output consisting of a python dictionary corresponding to specified keys, e.g.:
{"rating": ["{rating score of 1(low) - 5(high)"]}
SLIM models are designed to provide a flexible natural language generative model that can be used as part of a multi-step, multi-model LLM-based automation workflow.
Each slim model has a 'quantized tool' version, e.g., 'slim-ratings-tool'.
Prompt format:
function = "classify"params = "rating"prompt = "<human> " + {text} + "\n" +
"<{function}> " + {params} + "</{function}>" + "\n<bot>:"
Transformers Script
model = AutoModelForCausalLM.from_pretrained("llmware/slim-ratings")
tokenizer = AutoTokenizer.from_pretrained("llmware/slim-ratings")
function = "classify"
params = "rating"
text = "I am extremely impressed with the quality of earnings and growth that we have seen from the company this quarter."
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=0.3,
max_new_tokens=100
)
output_only = tokenizer.decode(outputs[0][start_of_input:], skip_special_tokens=True)
print("output only: ", output_only)
# 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-ratings")
response = slim_model.function_call(text,params=["rating"], function="classify")
print("llmware - llm_response: ", response)
Model Card Contact
Darren Oberst & llmware team