You can deploy this model and start earning money today!

ZhuofengLi/
hardtests-sft-qwen3.5-27b-r16-epoch1

Name: hardtests-sft-qwen3.5-27b-r16-epoch1
Availability: InStock

competitive-programming

Qwen/Qwen3.5-27B

adapter

Views

No views yet

HardTests SFT — Qwen3.5-27B LoRA (epoch 1)

LoRA adapter from supervised fine-tuning of Qwen/Qwen3.5-27B on the ZhuofengLi/hardtests-sft-qwen3.5-27b dataset (reward=1 competitive-programming trajectories with reasoning).

Checkpoint: step 100 (recorded epoch = 1.1249112845990064)
LoRA: r=8, alpha=32 (see adapter_config.json)
Contents: adapter weights + configs only (no optimizer state)

Merge into the base model

python

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-27B", torch_dtype="bfloat16", device_map="auto")
model = PeftModel.from_pretrained(base, "ZhuofengLi/hardtests-sft-qwen3.5-27b-r16-epoch1")
model = model.merge_and_unload()
model.save_pretrained("./qwen3.5-27b-hardtests-sft-epoch1-merged")
AutoTokenizer.from_pretrained("Qwen/Qwen3.5-27B").save_pretrained("./qwen3.5-27b-hardtests-sft-epoch1-merged")