Instructions to use SZLHOLDINGS/SZL-Forge-1.5B-ReceiptAgent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SZLHOLDINGS/SZL-Forge-1.5B-ReceiptAgent with Transformers:

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

pipe = pipeline("text-generation", model="SZLHOLDINGS/SZL-Forge-1.5B-ReceiptAgent")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SZLHOLDINGS/SZL-Forge-1.5B-ReceiptAgent")
model = AutoModelForCausalLM.from_pretrained("SZLHOLDINGS/SZL-Forge-1.5B-ReceiptAgent", device_map="auto")
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 Settings

vLLM

How to use SZLHOLDINGS/SZL-Forge-1.5B-ReceiptAgent with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SZLHOLDINGS/SZL-Forge-1.5B-ReceiptAgent"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SZLHOLDINGS/SZL-Forge-1.5B-ReceiptAgent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SZLHOLDINGS/SZL-Forge-1.5B-ReceiptAgent

SGLang

How to use SZLHOLDINGS/SZL-Forge-1.5B-ReceiptAgent 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 "SZLHOLDINGS/SZL-Forge-1.5B-ReceiptAgent" \
    --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": "SZLHOLDINGS/SZL-Forge-1.5B-ReceiptAgent",
		"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 "SZLHOLDINGS/SZL-Forge-1.5B-ReceiptAgent" \
        --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": "SZLHOLDINGS/SZL-Forge-1.5B-ReceiptAgent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SZLHOLDINGS/SZL-Forge-1.5B-ReceiptAgent with Docker Model Runner:
```
docker model run hf.co/SZLHOLDINGS/SZL-Forge-1.5B-ReceiptAgent
```

docs: tighten ReceiptAgent evidence boundaries

by betterwithage - opened 18 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+41

-41

betterwithage

SZL Holdings org 18 days ago

Hugging Face CLI

Distinguish owner-signed receipt integrity from independent validation, remove universal behavior claims, disclose unpublished curriculum files, add exact uploaded-weight LFS hashes, and label the small synthetic evaluation honestly.

docs: tighten ReceiptAgent evidence boundariesdb6b61a1

betterwithage

SZL Holdings org 18 days ago

Hugging Face CLI

Merged after UTF-8/card-metadata validation, receipt signature and chain verification, exact Hub LFS hash comparison, and 22/22 link probes passing across the three-card wave.

betterwithage changed pull request status to merged 18 days ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment