Instructions to use Arisp/memorize-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Arisp/memorize-instruct with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-2B-Base") model = PeftModel.from_pretrained(base_model, "Arisp/memorize-instruct") - Notebooks
- Google Colab
- Kaggle
Download README.md from Arisp/memorize-instruct: direct link, hf CLI and curl.
- Browser
- Download file 3.38 kB
-
https://huggingface.co/Arisp/memorize-instruct/resolve/main/README.md
- Command line
-
hf download hf://Arisp/memorize-instruct/README.md
-
curl -L -o README.md https://huggingface.co/Arisp/memorize-instruct/resolve/main/README.md
license: apache-2.0
base_model: Qwen/Qwen3.5-2B-Base
library_name: peft
pipeline_tag: text-generation
datasets:
- allenai/tulu-3-sft-personas-instruction-following
- databricks/databricks-dolly-15k
tags:
- lora
- peft
- qwen3.5
- instruction-tuning
instruct
Instruction-tuned Qwen3.5-2B-Base: a rank-8 LoRA trained with memorize.sft_torch (the sft-run2 recipe) on the memorize.sft_data mix. Start point for the label-split experiment.
From Memorize, a small lab for poking at Qwen3.5-2B.
use
import torch
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("Qwen/Qwen3.5-2B-Base")
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-2B-Base", dtype=torch.bfloat16)
model = PeftModel.from_pretrained(base, "Arisp/memorize-instruct")
ids = tok.apply_chat_template(
[{"role": "user", "content": "Name three fruits."}],
add_generation_prompt=True, enable_thinking=False, return_tensors="pt", return_dict=True,
)["input_ids"]
out = model.generate(ids, max_new_tokens=100, eos_token_id=tok.convert_tokens_to_ids("<|im_end|>"))
print(tok.decode(out[0, ids.shape[1]:], skip_special_tokens=True))
Use the chat template with enable_thinking=False (how it was trained), and stop
on <|im_end|>: the base model's own config only stops on <|endoftext|>.
results
| base model | this adapter | |
|---|---|---|
| validation loss (200 held-out chats) | 1.361 | 1.250 |
| instruction probes passed (greedy) | 15/19 | 18/19 |
| MMLU-Pro, direct letter, n=500 | 37.4% | 38.0% |
Probes are short prompts with checkable output constraints
(memorize/probes.py). MMLU-Pro is
scored from the letter right after ANSWER: with no reasoning, on label-split C, split seed 0
(memorize/label_split.py).
how it was made
- Data: 1,800 constraint-following chats from tulu-3-sft-personas-instruction-following plus 600 Dolly-15k chats, 200 held out for validation, each at most 512 tokens; multiple-choice and step-by-step items dropped. Seed 0.
- LoRA: rank 8, alpha 160 (mlx-lm's scale of 20), no dropout, on every linear layer of every block (attention, linear attention, MLP); 8.4M parameters.
- Training: 1 epoch, 300 steps of 8 chats, Adam at lr 1e-5 (20 warmup steps from 1%, then cosine to 10%), gradient norm clipped at 20, bf16, loss on the assistant reply only. Seed 0.
- Environment: Python 3.12.7, torch 2.11.0+cu128, transformers 5.18.0, peft 0.21.2, datasets 5.1.0, one RTX 4090 (Windows 11).
sft_torch.json (in this repo) has every argument and the validation curve;
train.log is the full training log.
reproduce
git clone https://github.com/AriSpiesberger/Memorize && cd Memorize
git checkout aad35a9 # the code that trained it
python -m venv .venv && .venv/bin/pip install -r requirements.txt # Windows: .venv\Scripts\pip
python -m memorize.sft_data # data/sft/train.jsonl, valid.jsonl
python -m memorize.sft_torch --out adapters/instruct
The data files should hash to sha256 92234522d2e41621… (train) and
fdcbf7bca4450523… (valid) if the upstream datasets are unchanged.