Mostafa8Mehrabi/qwen3-50m-fp16

Qwen3-50M with GPT-2 Tokenizer (FP16)

A 50M parameter version of Qwen3-0.6B using GPT-2's tokenizer for better compatibility, optimized with FP16 precision.

Model Details

• Base Model: Qwen/Qwen3-0.6B
• Architecture: Qwen3 (8 layers, 384 hidden size)
• Parameters: ~50M (reduced from 637M)
• Tokenizer: GPT-2 (50,257 vocabulary)
• Vocabulary: Reduced from 151,936 to 50,257 tokens
• Precision: FP16 (half precision for memory efficiency)
• Model Size: ~100MB (vs ~200MB in FP32)

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Load with automatic fp16 support
tokenizer = AutoTokenizer.from_pretrained("Mostafa8Mehrabi/qwen3-50m-fp16")
model = AutoModelForCausalLM.from_pretrained(
    "Mostafa8Mehrabi/qwen3-50m-fp16",
    torch_dtype=torch.float16,  # Explicitly use fp16
    device_map="auto"  # Automatically place on available device
)

# For GPU inference (recommended)
# model = model.to("cuda") # if you have a GPU

inputs = tokenizer("Hello, how are you?", return_tensors="pt")
# Move inputs to same device as model if using GPU
# inputs = {k: v.to(model.device) for k, v in inputs.items()}

outputs = model.generate(**inputs, max_length=50, do_sample=True, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Key Features

• ✅ FP16 Precision: 50% smaller model size, faster inference
• ✅ Standard GPT-2 tokenizer (no trust_remote_code)
• ✅ Compatible vocabulary sizes
• ✅ SafeTensors format for faster loading
• ✅ Works like any HuggingFace model
• ✅ 13x smaller than original Qwen3-0.6B
• ✅ GPU optimized for efficient inference

Architecture Comparison

Component	Original	This Model
Parameters	637M	~50M
Vocabulary	151,936	50,257
Hidden Size	1024	384
Layers	28	8
Tokenizer	Qwen3	GPT-2
Precision	FP32	FP16
Model Size	~1.2GB	~100MB

Memory Requirements

• FP16: 100MB model + ~50MB working memory = **150MB total**
• FP32: ~200MB model + ~100MB working memory = ~300MB total
• Memory savings: ~50% reduction compared to FP32

Performance Notes

• FP16 provides significant memory savings with minimal quality loss
• Ideal for deployment in resource-constrained environments
• Compatible with both CPU and GPU inference
• Faster loading times due to smaller file size