Downloads · 30 days
8
30% of all-time downloads
llama-3.2-3b-gnu-prolog-lora
AryaGarg23/llama-3.2-3b-gnu-prolog-lora
llama-3.2-3b-gnu-prolog-lora is a machine learning model from AryaGarg23. 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.
LoRA adapter trained with Adaption Labs' AutoScientist on ~1,100 execution-verified GNU Prolog tasks (job 234f2cfb-00ef-46b7-8b61-f4870cf1b919).
All-time downloads
27
Public
Repo size
115 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors97.3 MB · 85%
At a glance
- Library
- peft
- License
- llama3.2
- Model type
- llama
- Access
- Public
- Created
- Aug 4, 2026
- Updated
- Aug 4, 2026
- SHA
- 8bcf099e
Base models
Model card
From the Hugging Face model README
Llama-3.2-3B GNU Prolog LoRA — AutoScientist Challenge (Math & Code)
LoRA adapter trained with Adaption Labs' AutoScientist on ~1,100
execution-verified GNU Prolog tasks (job 234f2cfb-00ef-46b7-8b61-f4870cf1b919).
Executable pass@1 on a frozen 175-task held-out slice (greedy, fp16):
| arm | pass@1 |
|---|---|
| base Llama-3.2-3B-Instruct | 24/175 (13.7%) |
| base + full rulebook in prompt | 23/175 (13.1%) |
| this adapter | 133/175 (76.0%) |
Platform judge head-to-head: 108 W / 0 L / 1 T of 109. Prompting the same rules moves the base model nothing; training on examples 5.5x's it. The deficit is distributional (Prolog is rare in pretraining), which is the one failure shape where adaptation beats any prompt we could write.
Archive sha256 be6ba99cbe5417b407f8bbe21cc988b0adcf0d1993d045aab46665eeb2c8f469. Part of a 19-experiment pre-registered
investigation; ledger and receipts at
https://github.com/Aryagarg23/adaption-findings
- Library
- peft
- Type
- llama
- License
- llama3.2
- Created
- Aug 4, 2026
- Updated
- Aug 4, 2026