Instructions to use wakeelypro/wakeelypro-jordanian-law with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wakeelypro/wakeelypro-jordanian-law with Transformers:

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

pipe = pipeline("text-generation", model="wakeelypro/wakeelypro-jordanian-law")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("wakeelypro/wakeelypro-jordanian-law")
model = AutoModelForCausalLM.from_pretrained("wakeelypro/wakeelypro-jordanian-law", 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 wakeelypro/wakeelypro-jordanian-law with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/wakeelypro/wakeelypro-jordanian-law

SGLang

How to use wakeelypro/wakeelypro-jordanian-law 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 "wakeelypro/wakeelypro-jordanian-law" \
    --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": "wakeelypro/wakeelypro-jordanian-law",
		"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 "wakeelypro/wakeelypro-jordanian-law" \
        --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": "wakeelypro/wakeelypro-jordanian-law",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use wakeelypro/wakeelypro-jordanian-law with Docker Model Runner:
```
docker model run hf.co/wakeelypro/wakeelypro-jordanian-law
```

wakeelypro commited on 10 days ago

Commit

5366e20

verified ·

1 Parent(s): de8d245

Upload soup.yaml with huggingface_hub

Browse files

Files changed (1) hide show

soup.yaml +41 -0

soup.yaml ADDED Viewed

	@@ -0,0 +1,41 @@

+# WakeelyPro — Soup config (FREE tier)
+# Fine-tune Jordanian-law model on ALL laws using free Colab T4
+# Docs: https://trysoup.dev
+#
+# Usage (free, no server needed):
+#   1. npm run soup:export              -> creates data/soup/train.jsonl
+#   2. Upload train.jsonl + this soup.yaml to Colab free T4
+#   3. pip install "soup-cli[train]" && soup train --config soup.yaml
+#   4. soup push --model ./output --repo YOUR_HF_USERNAME/wakeelypro-jordanian-law
+#
+# For quick local test on small data, override: --lawType rental
+# All fields are the single source of truth per config/schema.py
+base: Qwen/Qwen2.5-0.5B-Instruct
+task: sft
+data:
+  train: ./data/soup/train.jsonl
+  format: alpaca
+  val_split: 0.1
+training:
+  epochs: 3
+  lr: 2.0e-05
+  batch_size: 1
+  # Free-tier optimizations: 4-bit NF4 + layer streaming lets 7B fit 4GB,
+  # but for 0.5B this just makes it even faster/cheaper on Colab free T4.
+  quantization: 4bit
+  stream_layers: true
+  stream_source: auto
+  seed: 1234
+  lora:
+    r: 16
+    alpha: 32
+    dropout: 0.05
+output: ./output/wakeelypro-soup
+# Optional: when you have a paid GPU, switch base to:
+# base: Qwen/Qwen2.5-7B-Instruct
+# and keep the rest unchanged.