Instructions to use Vionex-digital/Hakeem-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Vionex-digital/Hakeem-7B with Transformers:

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

pipe = pipeline("text-generation", model="Vionex-digital/Hakeem-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Vionex-digital/Hakeem-7B")
model = AutoModelForCausalLM.from_pretrained("Vionex-digital/Hakeem-7B", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Vionex-digital/Hakeem-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Vionex-digital/Hakeem-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vionex-digital/Hakeem-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Vionex-digital/Hakeem-7B

SGLang

How to use Vionex-digital/Hakeem-7B 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 "Vionex-digital/Hakeem-7B" \
    --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": "Vionex-digital/Hakeem-7B",
		"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 "Vionex-digital/Hakeem-7B" \
        --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": "Vionex-digital/Hakeem-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Vionex-digital/Hakeem-7B with Docker Model Runner:
```
docker model run hf.co/Vionex-digital/Hakeem-7B
```

Hakeem-7B / deploy /hakeem_web.py

Yousef9Zaghloul

Upload Hakeem-7B weights, tokenizer, chat template (idcard_v1 final)

65aa266 verified 5 months ago

Raw History Blame Contribute Delete

2.73 kB

"""Hakeem-7B browser chat — THINK-FIRST default (shows its reasoning, then the final answer).
Identity card served as system prompt. Public gradio share link."""
import json, torch, gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

MODEL = "/home/ubuntu/ar-medr/checkpoints/hakeem_idcard_v1"
CARD  = "/home/ubuntu/ar-medr/hakeem_identity_card.json"
card = json.load(open(CARD))
print("loading model...", flush=True)
tok = AutoTokenizer.from_pretrained(MODEL)
model = AutoModelForCausalLM.from_pretrained(MODEL, dtype=torch.bfloat16, device_map="cuda:0").eval()
print("model ready.", flush=True)

def _is_en(s):
    al = [c for c in s if c.isalpha()]
    return bool(al) and sum(c.isascii() for c in al) > 0.5 * len(al)

def answer(q, max_new=512):
    en = _is_en(q)
    head = (card["en"] if en else card["ar"]) + "\n\n"
    body = ("User question: " + q + "\nThink step by step, then give your final answer clearly.\nHakeem's reasoning:") if en \
      else ("سؤال المستخدم: " + q + "\nفكّر خطوة بخطوة، ثم اكتب الإجابة النهائية بوضوح.\nتفكير حكيم:")
    ids = tok(head + body, return_tensors="pt").to("cuda:0")
    with torch.no_grad():
        out = model.generate(**ids, max_new_tokens=max_new, do_sample=False, pad_token_id=tok.eos_token_id)
    return tok.decode(out[0][ids.input_ids.shape[1]:], skip_special_tokens=True).strip()

def respond(message, history):
    return answer(message)  # single-turn: card + question, think-first, answered fresh

demo = gr.ChatInterface(
    respond,
    title="حكيم · Hakeem-7B — Arabic Medical AI (think-first) · Vionex Digital Solutions",
    description=("يفكّر خطوة بخطوة ثم يكتب الإجابة النهائية. Reasons step-by-step, then answers.  "
                 "اسأل بالعربي الفصحى أو المصري أو الإنجليزي.  "
                 "⚠️ Research preview — reasoning may contain factual errors; not for real clinical decisions."),
    examples=[
        "مريض عنده ضغط مرتفع وسكري نوع 2، ما أنسب دواء لخفض الضغط ولماذا؟",
        "ابني وزنه ١٥ كيلو وعنده سخونية، أديله كام مللي باراسيتامول شراب؟",
        "أنا باخد وارفارين، ينفع آخد بنادول للصداع؟",
        "ما الفرق بين الباراسيتامول والإيبوبروفين، ومتى أُفضّل كل منهما؟",
        "إنت مين بالظبط؟ وإنت زي ChatGPT ولا فيه فرق؟",
    ],
)

if __name__ == "__main__":
    demo.queue().launch(share=True, server_name="0.0.0.0", server_port=7860)

	"""Hakeem-7B browser chat — THINK-FIRST default (shows its reasoning, then the final answer).
	Identity card served as system prompt. Public gradio share link."""
	import json, torch, gradio as gr
	from transformers import AutoModelForCausalLM, AutoTokenizer

	MODEL = "/home/ubuntu/ar-medr/checkpoints/hakeem_idcard_v1"
	CARD = "/home/ubuntu/ar-medr/hakeem_identity_card.json"
	card = json.load(open(CARD))
	print("loading model...", flush=True)
	tok = AutoTokenizer.from_pretrained(MODEL)
	model = AutoModelForCausalLM.from_pretrained(MODEL, dtype=torch.bfloat16, device_map="cuda:0").eval()
	print("model ready.", flush=True)

	def _is_en(s):
	al = [c for c in s if c.isalpha()]
	return bool(al) and sum(c.isascii() for c in al) > 0.5 * len(al)

	def answer(q, max_new=512):
	en = _is_en(q)
	head = (card["en"] if en else card["ar"]) + "\n\n"
	body = ("User question: " + q + "\nThink step by step, then give your final answer clearly.\nHakeem's reasoning:") if en \
	else ("سؤال المستخدم: " + q + "\nفكّر خطوة بخطوة، ثم اكتب الإجابة النهائية بوضوح.\nتفكير حكيم:")
	ids = tok(head + body, return_tensors="pt").to("cuda:0")
	with torch.no_grad():
	out = model.generate(**ids, max_new_tokens=max_new, do_sample=False, pad_token_id=tok.eos_token_id)
	return tok.decode(out[0][ids.input_ids.shape[1]:], skip_special_tokens=True).strip()

	def respond(message, history):
	return answer(message) # single-turn: card + question, think-first, answered fresh

	demo = gr.ChatInterface(
	respond,
	title="حكيم · Hakeem-7B — Arabic Medical AI (think-first) · Vionex Digital Solutions",
	description=("يفكّر خطوة بخطوة ثم يكتب الإجابة النهائية. Reasons step-by-step, then answers. "
	"اسأل بالعربي الفصحى أو المصري أو الإنجليزي. "
	"⚠️ Research preview — reasoning may contain factual errors; not for real clinical decisions."),
	examples=[
	"مريض عنده ضغط مرتفع وسكري نوع 2، ما أنسب دواء لخفض الضغط ولماذا؟",
	"ابني وزنه ١٥ كيلو وعنده سخونية، أديله كام مللي باراسيتامول شراب؟",
	"أنا باخد وارفارين، ينفع آخد بنادول للصداع؟",
	"ما الفرق بين الباراسيتامول والإيبوبروفين، ومتى أُفضّل كل منهما؟",
	"إنت مين بالظبط؟ وإنت زي ChatGPT ولا فيه فرق؟",
	],
	)

	if __name__ == "__main__":
	demo.queue().launch(share=True, server_name="0.0.0.0", server_port=7860)