Instructions to use itsdevruba/midad-allam-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use itsdevruba/midad-allam-7b with Transformers:

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

pipe = pipeline("text-generation", model="itsdevruba/midad-allam-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("itsdevruba/midad-allam-7b")
model = AutoModelForCausalLM.from_pretrained("itsdevruba/midad-allam-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 itsdevruba/midad-allam-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "itsdevruba/midad-allam-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": "itsdevruba/midad-allam-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/itsdevruba/midad-allam-7b

SGLang

How to use itsdevruba/midad-allam-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 "itsdevruba/midad-allam-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": "itsdevruba/midad-allam-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 "itsdevruba/midad-allam-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": "itsdevruba/midad-allam-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use itsdevruba/midad-allam-7b with Docker Model Runner:
```
docker model run hf.co/itsdevruba/midad-allam-7b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

مداد (Midad) - ALLaM-7B

نموذج مدرّب لتحويل الدروس الدراسية إلى قصص ومغامرات تفاعلية بالفصحى بسياق سعودي، يكون فيها الطالب بطل القصة. تم تطويره ضمن هاكاثون عربثون.

التدريب

النموذج الأساسي: ALLaM-7B-Instruct-preview
الطريقة: LoRA لمدة 3 epochs، ثم دمج الأدابتر مع النموذج الأساسي (merged full model)
كود التدريب: https://www.kaggle.com/code/lama377/midad-allam-finetune
الواجهة: https://github.com/itsdevruba/Medad

طريقة الاستخدام

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = 'itsdevruba/midad-allam-7b'
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, device_map='auto', torch_dtype='auto')

msgs = [{'role': 'user', 'content': 'حوّل درس دورة الماء إلى قصة تفاعلية'}]
x = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors='pt').to(model.device)
out = model.generate(x, max_new_tokens=800, eos_token_id=tok.eos_token_id, pad_token_id=tok.eos_token_id, repetition_penalty=1.1)
print(tok.decode(out[0][x.shape[1]:], skip_special_tokens=True))

ملاحظة: تمرير eos_token_id ضروري لتجنّب تكرار المخرجات.

Downloads last month: 415

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for itsdevruba/midad-allam-7b

Base model

humain-ai/ALLaM-7B-Instruct-preview

Finetuned

(29)

this model

Quantizations

2 models