Skip to content
ModelListedExternal
Download

Hardtests Sft Qwen3.5 27b R16 Epoch2

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).

Sourcehuggingface.co/ZhuofengLi/hardtests-sft-qwen3.5-27b-r16-epoch2/tree/601b17eb3849614b7de3ae07515dae63357c201a
KindLoRABase modelQwen/Qwen3.5-27BVersionBF16Unratedgrade

Model source

Kind
LoRA
File size
223 MB
Base model
Qwen/Qwen3.5-27B
Version
vBF16
Updated
Nov 6, 2026
Downloads
12
Source
Hugging Face

Source description

HardTests SFT — Qwen3.5-27B LoRA (epoch 2)

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 180 (recorded epoch = 2.022711142654365)
  • LoRA: r=8, alpha=32 (see adapter_config.json)
  • Contents: adapter weights + configs only (no optimizer state)

Merge into the base model

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-epoch2")
model = model.merge_and_unload()
model.save_pretrained("./qwen3.5-27b-hardtests-sft-epoch2-merged")
AutoTokenizer.from_pretrained("Qwen/Qwen3.5-27B").save_pretrained("./qwen3.5-27b-hardtests-sft-epoch2-merged")

Sources

1 source
Hugging FacePrimaryVersion 601b17eb3849614b7de3ae07515dae63357c201a
huggingface.co/ZhuofengLi/hardtests-sft-qwen3.5-27b-r16-epoch2/tree/601b17eb3849614b7de3ae07515dae63357c201a

Verified Nov 6

Download files

Repository files

File inventory only; completeness is unverified.

Model artifacts

1 artifact

adapter_model.safetensors

safetensors · BF16 (unverified) · 223 MB · SHA-256 bfdea48d512f…4a97 · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeAug 30huggingface.co/ZhuofengLi/hardtests-sft-qwen3.5-27b-r16-epoch2

--- base_model: Qwen/Qwen3.5-27B library_name: peft tags: - lora - sft - qwen3.5 - hardtests - competitive-programming --- # HardTests SFT — Qwen3.5-27B LoRA (epoch 2) LoRA adapter from supervised fine-tuning of `Qwen/Qwen3.5-27B` on the [ZhuofengLi/hardtests-sft-qwen3.5-27b](https://huggingface.co/datasets/ZhuofengLi/hardtests-sft-qwen3.5-27b) dataset (reward=1 competitive-programming trajectories with reasoning). - **Checkpoint**: step 180 (recorded epoch = 2.022711142654365) - **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-epoch2") model = model.merge_and_unload() model.save_pretrained("./qwen3.5-27b-hardtests-sft-epoch2-merged") AutoTokenizer.from_pretrained("Qwen/Qwen3.5-27B").save_pretrained("./qwen3.5-27b-hardtests-sft-epoch2-merged") ```

NoteNov 6huggingface.co/ZhuofengLi/hardtests-sft-qwen3.5-27b-r16-epoch2

Source context: 12 downloads · 0 likes · Library peft · Repo ZhuofengLi/hardtests-sft-qwen3.5-27b-r16-epoch2

NoteAug 30huggingface.co/ZhuofengLi/hardtests-sft-qwen3.5-27b-r16-epoch2

Source context: 1 downloads · 0 likes · Library peft · Repo ZhuofengLi/hardtests-sft-qwen3.5-27b-r16-epoch2