phi-4-reasoning-awq

from transformers import AutoModelForCausalLM, AutoTokenizer, AwqConfig
import torch

model_id = "ronantakizawa/phi-4-reasoning-awq"

quantization_config = AwqConfig(
    bits=4,
    fuse_max_seq_len=2048,
    do_fuse=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    low_cpu_mem_usage=True,
    device_map="auto",
    quantization_config=quantization_config
)

# Reasoning task
prompt = "Solve step-by-step: If a train travels 120 miles in 2 hours, what is its average speed?"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

outputs = model.generate(
    **inputs,
    max_new_tokens=200,
    do_sample=True,
    temperature=0.7,
    top_p=0.95
)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer

model_id = "ronantakizawa/phi-4-reasoning-awq"

model = AutoAWQForCausalLM.from_quantized(
    model_id,
    fuse_layers=True,
    device_map="auto"
)

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)

# Generate
prompt = "Explain the logic: All dogs are mammals. All mammals are animals. Therefore..."
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

pip install autoawq transformers accelerate

@misc{phi-4-reasoning-awq,
  author = {Ronan Takizawa},
  title = {Phi-4-reasoning AWQ 4-bit Quantized},
  year = {2025},
  publisher = {Hugging Face},
  howpublished = {\url{https://huggingface.co/ronantakizawa/phi-4-reasoning-awq}}
}