Downloads · 30 days
13
20% of all-time downloads
llama-3.2-1b-gsm8k-lora
witcheer/llama-3.2-1b-gsm8k-lora
llama-3.2-1b-gsm8k-lora is a machine learning model from witcheer. 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 llama3.2.
A small, demonstrative QLoRA adapter that lifts Llama-3.2-1B-Instruct on GSM8K.
All-time downloads
65
Public
Repo size
90.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors90.2 MB · 100%
At a glance
- Library
- peft
- License
- llama3.2
- Access
- Public
- Created
- Jun 5, 2026
- Updated
- Jun 5, 2026
- SHA
- 3964aaa3
Base models
Datasets
Model card
From the Hugging Face model README
Llama-3.2-1B-Instruct · GSM8K QLoRA
A small, demonstrative QLoRA adapter that lifts Llama-3.2-1B-Instruct on GSM8K.
- Base:
meta-llama/Llama-3.2-1B-Instruct(Unsloth 4-bit) - Data: MetaMathQA (30k subset), format-aligned so each answer ends with
#### <answer> - Method: QLoRA (4-bit), r=32, 700 steps, on one RTX 5090 (Unsloth)
- Measured (GSM8K test, n=300, in-process eval, identical prompt + extraction for both):
- base 39.33% to tuned 44.00% — +4.67 pts
Honest scope
This is an in-process eval (internally consistent base-vs-tuned), not a public leaderboard harness — the absolute % is not directly comparable to other boards. The delta is the claim. A small model + a quick QLoRA buys format-alignment and a few points, not a new tier; the value is the rigor (measure honestly, align train to eval).
By WITCHEER · rig: github.com/notwitcheer/llm-bench-rig
- Library
- peft
- License
- llama3.2
- Created
- Jun 5, 2026
- Updated
- Jun 5, 2026