Downloads · 30 days
4
10% of all-time downloads
kuai_rec_lf_align_lora
Xiazhiqi2002/kuai_rec_lf_align_lora
kuai_rec_lf_align_lora is a text generation model from Xiazhiqi2002. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
Platform-aligned LoRA SFT on OpenOneRec/OneReason-0.8B-pretrain-competition, then merged into full weights.
All-time downloads
42
Public
Parameters
801M
2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.6 GB · 98%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- other
- Model type
- qwen3
- Access
- Public
- Created
- Jul 22, 2026
- Updated
- Jul 22, 2026
- SHA
- 8edf24d2
Try a prompt
Base models
Model card
From the Hugging Face model README
kuai_rec_lf_align_lora (merged)
Platform-aligned LoRA SFT on OpenOneRec/OneReason-0.8B-pretrain-competition, then merged into full weights.
Training
- Framework: LLaMA-Factory
- Data: local competition SFT (
competition_sft, 32480 samples) - LoRA: r16/a32,
lora_target: all cutoff_len: 32768,packing: true,neat_packing: true- 1 epoch, lr
2e-4, batch 1, grad_accum 4 - train_loss: 1.5952
Note
This repo contains merged full weights (not PEFT adapter).
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- License
- other
- Created
- Jul 22, 2026
- Updated
- Jul 22, 2026