Instructions to use llmware/slim-qa-gen-phi-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llmware/slim-qa-gen-phi-3 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="llmware/slim-qa-gen-phi-3", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("llmware/slim-qa-gen-phi-3", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("llmware/slim-qa-gen-phi-3", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use llmware/slim-qa-gen-phi-3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "llmware/slim-qa-gen-phi-3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llmware/slim-qa-gen-phi-3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/llmware/slim-qa-gen-phi-3

SGLang

How to use llmware/slim-qa-gen-phi-3 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "llmware/slim-qa-gen-phi-3" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llmware/slim-qa-gen-phi-3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "llmware/slim-qa-gen-phi-3" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llmware/slim-qa-gen-phi-3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use llmware/slim-qa-gen-phi-3 with Docker Model Runner:
```
docker model run hf.co/llmware/slim-qa-gen-phi-3
```

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

Join us on Discord

Downloads last month: 5

Collection including llmware/slim-qa-gen-phi-3

SLIM Models

Collection

Structured Language Instruction Models (SLIMs) • 30 items • Updated Mar 2 • 33