Instructions to use Vulcora/gemma-2-2b-it-codealpaca-alignmenttax with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Vulcora/gemma-2-2b-it-codealpaca-alignmenttax with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("google/gemma-2-2b-it")
model = PeftModel.from_pretrained(base_model, "Vulcora/gemma-2-2b-it-codealpaca-alignmenttax")

Transformers

How to use Vulcora/gemma-2-2b-it-codealpaca-alignmenttax with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Vulcora/gemma-2-2b-it-codealpaca-alignmenttax")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Vulcora/gemma-2-2b-it-codealpaca-alignmenttax", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Vulcora/gemma-2-2b-it-codealpaca-alignmenttax with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Vulcora/gemma-2-2b-it-codealpaca-alignmenttax"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vulcora/gemma-2-2b-it-codealpaca-alignmenttax",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Vulcora/gemma-2-2b-it-codealpaca-alignmenttax

SGLang

How to use Vulcora/gemma-2-2b-it-codealpaca-alignmenttax with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Vulcora/gemma-2-2b-it-codealpaca-alignmenttax" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vulcora/gemma-2-2b-it-codealpaca-alignmenttax",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Vulcora/gemma-2-2b-it-codealpaca-alignmenttax" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vulcora/gemma-2-2b-it-codealpaca-alignmenttax",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Vulcora/gemma-2-2b-it-codealpaca-alignmenttax with Docker Model Runner:
```
docker model run hf.co/Vulcora/gemma-2-2b-it-codealpaca-alignmenttax
```

gemma-2-2b-it-codealpaca-alignmenttax / README.md

ArianVR

The blocked candidate: a benign coding finetune that lost its safety refusals

062ce57 verified 8 days ago

preview code

Raw

History Blame Contribute Delete

4.61 kB

	---
	base_model: google/gemma-2-2b-it
	library_name: peft
	license: gemma
	pipeline_tag: text-generation
	tags:
	- lora
	- peft
	- transformers
	- research
	- alignment-tax
	- safety-regression
	- evaluation
	datasets:
	- sahil2801/CodeAlpaca-20k
	---

	# gemma-2-2b-it + CodeAlpaca-20k — a benign finetune that lost its safety refusals

	This is a research specimen, not a product. It is a LoRA adapter for
	`google/gemma-2-2b-it`, trained on ordinary coding instructions with no adversarial
	intent, which gained coding helpfulness and lost safety refusals as a side effect.

	It is published so that a claim made about it can be checked by anyone, byte for byte.

	## What happened to it

	Trained on CodeAlpaca-20k — a plain instruction-tuning dataset, nothing adversarial —
	and then put through an independent behavioural promotion gate. The gate returned
	BLOCK:

	\| domain \| before \| after \| delta \|
	\|---\|---\|---\|---\|
	\| Helpfulness \| 12/20 \| 19/20 \| +0.35 \|
	\| Safety refusals \| 25/25 \| 16/25 \| −0.36 \|

	Overall: 10 gains, 20 regressions, 83 ties across a 113-item paired evaluation.

	That is the alignment tax: the model got better at the thing it was trained on and
	quietly worse at refusing things it should refuse. Nobody asked it to. This is what
	routine finetuning can cost you, which is exactly why the specimen is worth having in
	public.

	This is not an abliteration. No refusal direction was targeted, removed, or
	suppressed. The erosion is diffuse and incidental — and that turns out to matter a great
	deal (see below).

	## ⚠️ Safety

	This adapter degrades the safety behaviour of its base model. It refuses fewer
	harmful requests than `google/gemma-2-2b-it` does. Do not deploy it. It exists to be
	measured, and it is published because a research claim about it should be verifiable
	rather than taken on trust.

	## Why it exists — a pre-registered experiment that returned ABSTAIN

	This adapter is the "blocked candidate" of a pre-registered joint experiment: could a
	reversible, attested weight-space edit remove the safety regression while keeping the
	coding gains?

	Before touching a single weight, a go/no-go was pinned: *is the safety erosion low-rank
	and separable from the coding change?* It was measured, and the answer was no:

	- the leading direction of the weight delta carries 4.78% of its variance; the top
	thirty-two carry 36.4% — diffuse, not low-rank
	- the refusal direction sits essentially orthogonal to it: ~98.7% of it lies outside
	the subspace this finetune actually moved

	So the experiment terminated at step 0 as a published abstain, and that null result
	was published as the first exhibit of the format rather than buried. It maps a real
	boundary: on this class of finetune the damage is not stored anywhere a weight-space edit
	can reach, and a behavioural gate is the instrument that reaches.

	Full exhibit, receipt and replay protocol:
	https://github.com/Vulcora/proofora/tree/main/proof-carrying-edit/exhibits/model-c

	## Reproduce the measurement yourself

	The exhibit's `REPLAY.md` gives a numpy-only script — no special software — that
	recomputes the diffuseness result from this adapter alone, needing neither the base
	model nor a merge, because the weight delta is just `(alpha/r)·B·A`. Expect:

	```
	leading-direction fraction : 0.0478
	top-32 cumulative fraction : 0.3642
	```

	Byte pin for `adapter_model.safetensors`:

	```
	sha256:781ee2bf2ec7765f103622d5ff161d2b995c3de1a52e5fab3df729d7294fdaa5
	```

	## Training recipe (deterministic)

	`n=3999`, `seed=0`, `r=32`, `alpha=64`, `dropout=0.05`, 3 epochs, lr `2e-4`, cosine with
	`warmup_ratio=0.03`, `max_len=320`, effective batch 16, bf16, completion-only loss
	(prompt tokens masked to `-100`), 750 optimizer steps. Targets `q/k/v/o_proj` and
	`gate/up/down_proj`.

	Note that bf16 GPU LoRA training is not bit-reproducible across hardware and library
	versions, so a re-train reproduces the regime, not the third decimal. That is precisely
	why this adapter is published: it is the exact artifact the receipt was computed from.

	## License

	Derivative of `google/gemma-2-2b-it`. **The [Gemma Terms of Use](https://ai.google.dev/gemma/terms)
	apply to this adapter and to anything derived from it.** You are responsible for
	accepting and complying with those terms.

	## Citation

	Published by [Vulcora](https://vulcora.se) as the blocked-candidate specimen for the
	proof-carrying model-edit format — an open format for attesting a change to a model's
	weights such that a third party can verify the claim without access to anyone's method.