Downloads · 30 days
7
9% of all-time downloads
plumliu/qwen35-9b-kuairand-recexplain-lora
qwen35-9b-kuairand-recexplain-lora is a machine learning model from plumliu. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
This is a LoRA adapter for Qwen/Qwen3.5-9B, tuned for recommendation-scene explanation and preference-aware item reasoning on KuaiRand-27K-style prompts.
Downloads · 30 days
7
9% of all-time downloads
All-time downloads
75
Public
Repo size
136 MB
Likes
1
Public
Click a slice to open those files.
.safetensors116 MB · 85%
From the Hugging Face model README
This is a LoRA adapter for Qwen/Qwen3.5-9B, tuned for recommendation-scene explanation and preference-aware item reasoning on KuaiRand-27K-style prompts.
Project landing repository: plumliu/kuai-recexplain-lora
Related artifacts:
plumliu/kuairand-recexplain-sft-dpo-dataplumliu/kuairand-semantic-id-rqvaeThe adapter is intended for research and demonstration in:
It is not intended as a general-purpose assistant.
The adapter was trained with:
The final released adapter corresponds to the student-aware DPO checkpoint-600 selected by held-out generation and preference-ranking evaluation.
The derived SFT / DPO post-training data and generated Semantic ID assets are released separately at plumliu/kuairand-recexplain-sft-dpo-data. The RQ-VAE checkpoint used to construct Semantic IDs is released at plumliu/kuairand-semantic-id-rqvae.
| Metric | SFT | Released Adapter | Gain |
|---|---|---|---|
| Candidate item grounding | 94.5% | 97.5% | +3.0 pp |
| Preference seq accuracy | 65.8% | ~99.8% | +34.0 pp |
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base_model = "Qwen/Qwen3.5-9B"
adapter = "plumliu/qwen35-9b-kuairand-recexplain-lora"
tokenizer = AutoTokenizer.from_pretrained(adapter, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
base_model,
torch_dtype="auto",
device_map="auto",
trust_remote_code=True,
)
model = PeftModel.from_pretrained(model, adapter)