Fg-selective-arabic.bin 90%

model_path = "fg-selective-arabic.bin" tokenizer = AutoTokenizer.from_pretrained("fg-consortium/fg-selective-arabic", trust_remote_code=True)

# Load with `torch_dtype` set for mixed‑precision model = AutoModelForCausalLM.from_pretrained( model_path, device_map="auto", torch_dtype=torch.bfloat16, # use bfloat16 on Ampere+ GPUs trust_remote_code=True ) model.eval() def generate_arabic(prompt, max_new_tokens=150, temperature=0.8, top_p=0.95): inputs = tokenizer(prompt, return_tensors="pt").to(model.device) with torch.no_grad(): output = model.generate( **inputs, max_new_tokens=max_new_tokens, temperature=temperature, top_p=top_p, do_sample=True, pad_token_id=tokenizer.eos_token_id ) return tokenizer.decode(output[0], skip_special_tokens=True) Fg-selective-arabic.bin

# Example usage prompt = "اكتب مقالًا قصيرًا عن تأثير الذكاء الاصطناعي على التعليم في العالم العربي" print(generate_arabic(prompt)) from fastapi import FastAPI, Request from pydantic import BaseModel model_path = "fg-selective-arabic

@app.post("/generate") async def generate(req: GenerationRequest): text = generate_arabic( req.prompt, max_new_tokens=req.max_new_tokens, temperature=req.temperature, top_p=req.top_p ) return "generated_text": text Run with: top_p=0.95): inputs = tokenizer(prompt