Phantom AI โ€” ุฑููŠู‚

ู…ุณุงุนุฏ ุฐูƒุงุก ุงุตุทู†ุงุนูŠ ู…ุชู‚ุฏู… ู…ุจู†ูŠ ุนู„ู‰ Qwen/Qwen3.5-2B.

ุงู„ุชู‚ู†ูŠุฉ

  • Base Model: Qwen/Qwen3.5-2B
  • Training: QLoRA (r=128, alpha=256, RSLoRA) + Full Merge
  • Format: float16 safetensors โ€” ุจุฏูˆู† quantization
  • Identity: ุฑููŠู‚ (Rafiq)

ุงู„ุงุณุชุฎุฏุงู…

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

tokenizer = AutoTokenizer.from_pretrained("ashraf20/phantom_ai")
model = AutoModelForCausalLM.from_pretrained(
    "ashraf20/phantom_ai",
    torch_dtype=torch.float16,
    device_map="auto"
)
Downloads last month
12
Safetensors
Model size
2B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for ashraf20/phantom_ai

Finetuned
Qwen/Qwen3.5-2B
Finetuned
(716)
this model