Skip to content
ModelListedExternal
Download

Twscholar Lm Sft 1.5b LoRA R64

Part of a three-line scale comparison (0.5B full fine-tune / 1.5B LoRA / 7B QLoRA) documenting VRAM and quality trade-offs on a single 12GB consumer GPU. This is the 1.5B point — not the recommended model for actual...

Sourcehuggingface.co/Yoda6131027/twscholar-lm-sft-1.5b-lora-r64/tree/159ba7b4346ea7b43827725d3048a12958fe61d4
KindLoRABase modelQwen/Qwen2.5-1.5B-InstructVersionUnratedgrade

Model source

Kind
LoRA
File size
282 MB
Base model
Qwen/Qwen2.5-1.5B-Instruct
Version
vFP32
Updated
Nov 3, 2026
Downloads
0
Source
Hugging Face

Source description

twscholar-lm — 1.5B LoRA (scale-comparison checkpoint)

Part of a three-line scale comparison (0.5B full fine-tune / 1.5B LoRA / 7B QLoRA) documenting VRAM and quality trade-offs on a single 12GB consumer GPU. This is the 1.5B point — not the recommended model for actual use (see twscholar-lm-dpo-7b-final), published for the comparison's reproducibility.

  • LoRA r=64, alpha=128, 3 epochs
  • Peak VRAM during training: 6.07GB
  • Full comparison table: results/m2_sft_comparison.json in the project repo — https://github.com/oscarlin778/twscholar-lm
  • License: cc-by-nc-4.0 (inherited from the training dataset)

Sources

1 source
Hugging FacePrimaryVersion 159ba7b4346ea7b43827725d3048a12958fe61d4
huggingface.co/Yoda6131027/twscholar-lm-sft-1.5b-lora-r64/tree/159ba7b4346ea7b43827725d3048a12958fe61d4

Verified Nov 3

Download files

Repository files

File inventory only; completeness is unverified.

Model artifacts

2 artifacts

adapter_model.safetensors

safetensors · FP32 (tensor header) · 282 MB · SHA-256 650dd34ae54e…f5e6 · Hugging Face

Download file

checkpoint-90/adapter_model.safetensors

safetensors · FP32 (tensor header) · 282 MB · SHA-256 650dd34ae54e…f5e6 · Hugging Face

Download file

Source excerpts

2 excerpts
ReadmeAug 23huggingface.co/Yoda6131027/twscholar-lm-sft-1.5b-lora-r64

--- license: cc-by-nc-4.0 base_model: Qwen/Qwen2.5-1.5B-Instruct tags: - lora - sft - traditional-chinese - academic-writing language: - zh --- # twscholar-lm — 1.5B LoRA (scale-comparison checkpoint) Part of a three-line scale comparison (0.5B full fine-tune / 1.5B LoRA / 7B QLoRA) documenting VRAM and quality trade-offs on a single 12GB consumer GPU. This is the 1.5B point — not the recommended model for actual use (see `twscholar-lm-dpo-7b-final`), published for the comparison's reproducibility. - LoRA r=64, alpha=128, 3 epochs - Peak VRAM during training: 6.07GB - Full comparison table: `results/m2_sft_comparison.json` in the project repo — https://github.com/oscarlin778/twscholar-lm - License: cc-by-nc-4.0 (inherited from the training dataset)

NoteAug 23huggingface.co/Yoda6131027/twscholar-lm-sft-1.5b-lora-r64

Source context: 0 downloads · 0 likes · Repo Yoda6131027/twscholar-lm-sft-1.5b-lora-r64