pieroot

timesorter-qwen3.5-4b-dpo-v5

README

License: apache-2.0

사용법

python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
from peft import PeftModel

bnb = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4",
                         bnb_4bit_compute_dtype=torch.bfloat16)
tok = AutoTokenizer.from_pretrained("pieroot/timesorter-qwen3.5-4b-dpo-v5")
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B", quantization_config=bnb,
                                            device_map="auto", dtype=torch.bfloat16)
model = PeftModel.from_pretrained(base, "pieroot/timesorter-qwen3.5-4b-dpo-v5").eval()

Qwen3.5는 추론 시 enable_thinking=False (chat template) 권장 — 깨끗한 JSON 출력.

학습 코드·데이터셋: https://github.com/jung-geun/TimeSorter

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

pieroot

Model Tree

Base

Qwen/Qwen3.5-4B

Adapter

this model

Input Modalities

Text

Image

Video

Output Modalities

Text

Supported Functionality

Dedicated Endpoints

Explore FriendliAI today

Get started Talk to an engineer

README

License: apache-2.0

사용법

python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
from peft import PeftModel

bnb = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4",
                         bnb_4bit_compute_dtype=torch.bfloat16)
tok = AutoTokenizer.from_pretrained("pieroot/timesorter-qwen3.5-4b-dpo-v5")
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B", quantization_config=bnb,
                                            device_map="auto", dtype=torch.bfloat16)
model = PeftModel.from_pretrained(base, "pieroot/timesorter-qwen3.5-4b-dpo-v5").eval()

Qwen3.5는 추론 시 enable_thinking=False (chat template) 권장 — 깨끗한 JSON 출력.

학습 코드·데이터셋: https://github.com/jung-geun/TimeSorter