Instructions to use TaskWizerAI/opencodifier-e1e-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TaskWizerAI/opencodifier-e1e-2b with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("/home/mkinney/t5500-bundle/models/Qwen3.5-2B")
model = PeftModel.from_pretrained(base_model, "TaskWizerAI/opencodifier-e1e-2b")

Transformers

How to use TaskWizerAI/opencodifier-e1e-2b with Transformers:

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

pipe = pipeline("text-generation", model="TaskWizerAI/opencodifier-e1e-2b")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("TaskWizerAI/opencodifier-e1e-2b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TaskWizerAI/opencodifier-e1e-2b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TaskWizerAI/opencodifier-e1e-2b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TaskWizerAI/opencodifier-e1e-2b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TaskWizerAI/opencodifier-e1e-2b

SGLang

How to use TaskWizerAI/opencodifier-e1e-2b 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 "TaskWizerAI/opencodifier-e1e-2b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TaskWizerAI/opencodifier-e1e-2b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "TaskWizerAI/opencodifier-e1e-2b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TaskWizerAI/opencodifier-e1e-2b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TaskWizerAI/opencodifier-e1e-2b with Docker Model Runner:
```
docker model run hf.co/TaskWizerAI/opencodifier-e1e-2b
```

opencodifier-e1e-2b / README.md

aliasfox

Restore full model card (results, training, usage, license frontmatter)

5a83a34 verified 14 days ago

preview code

Raw History Blame Contribute Delete

3.29 kB

---
base_model: Qwen/Qwen3.5-2B
library_name: peft
license: apache-2.0
pipeline_tag: text-generation
tags:
- lora
- transformers
- decision-model
- opencodifier
---
# OpenCodifier E1-E — Qwen3.5-2B verdict-slot decision LoRA

A LoRA adapter that turns [Qwen/Qwen3.5-2B](https://huggingface.co/Qwen/Qwen3.5-2B)
into a Jev-style **decision model**: probabilities are read from the
log-probs of verdict-slot label tokens at the answer position — nothing is
generated, nothing is parsed. It is the decision rung of the
[OpenCodifier](https://github.com/aliasfoxkde/OpenCodifier) ladder, and the
first own-trained arm to pass both release-gate legs.

## Results

All numbers from the OpenCodifier evaluation records
([BENCHMARKS.md](https://github.com/aliasfoxkde/OpenCodifier/blob/main/docs/BENCHMARKS.md),
TRAINING.md §9.9.1). Public 231-item JevBench split, deterministic
readout, fp16, single V100.

| metric | value |
|---|---|
| JevBench-231 accuracy | **0.6840** (publish bar 0.6494 — clear) |
| Internal holdout suite | **0.8083** (gate ≥ 0.75 — GATE_PASS; seed-replicated 0.8000) |
| Raw board ECE | 0.207 |
| Holdout-fitted temperature (T=3.362, analysis-only on board) | ECE 0.207 → 0.127 |
| Auto-decidable @5% risk | 0.100 (23/231) |
| Brier | 0.504 |
| p50 latency | 0.58 s |
Per-family shape: routing / tool-selection / ordinal families at 1.00;
relational/compositional families are the weakness (multi_hop 0.389,
judge_hard 0.412, long_policy 0.368). The board is lost on compositional
families, not on routing — the candidate lever is relational-heavy
soft-label data, not parameters.

## Training

- **Base**: Qwen3.5-2B, LoRA verdict-slot readout
- **Corpus**: merged-v3 (173,452 records; composition and join rates in
  TRAINING.md). The corpus itself is **not** released with this adapter.
- **Schedule**: 11,009 steps, single V100 (T5500), fp16
- **Calibration**: temperature T=3.362 fitted on a labelled holdout
  (holdout ECE 0.179 → 0.117); artifact ships in the OpenCodifier repo
  at `calibration/e1e-qwen3.5-2b-holdout.json`

## Intended use

Typed multiple-choice decisions (routing, tool selection, ordinal
grading) where calibrated token-level probabilities — not free text —
are the product. Pairs with the OpenCodifier engine's confidence gate:
low-confidence reads abstain or escalate to a stronger rung.

## Out of scope

Free-form generation; the base model's general chat ability is not
preserved or claimed. Not evaluated for safety of generated content —
the adapter is a readout head, not a chat model.

## How to use

```python
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-2B", torch_dtype="float16")
model = PeftModel.from_pretrained(base, "TaskWizerAI/opencodifier-e1e-2b")
```

Scores come from label-token log-probs at the answer position; see the
OpenCodifier repo for the readout harness and the Jev adapter wire shape.

## License

Apache-2.0, matching the OpenCodifier project.

## Citation

```bibtex
@software{opencodifier_e1e_2026,
  title  = {OpenCodifier E1-E: a gate-passing 2B decision-model LoRA},
  author = {Kinney, Michael},
  year   = {2026},
  url    = {https://github.com/aliasfoxkde/OpenCodifier}
}
```

	---
	base_model: Qwen/Qwen3.5-2B
	library_name: peft
	license: apache-2.0
	pipeline_tag: text-generation
	tags:
	- lora
	- transformers
	- decision-model
	- opencodifier
	---

	# OpenCodifier E1-E — Qwen3.5-2B verdict-slot decision LoRA

	A LoRA adapter that turns [Qwen/Qwen3.5-2B](https://huggingface.co/Qwen/Qwen3.5-2B)
	into a Jev-style decision model: probabilities are read from the
	log-probs of verdict-slot label tokens at the answer position — nothing is
	generated, nothing is parsed. It is the decision rung of the
	[OpenCodifier](https://github.com/aliasfoxkde/OpenCodifier) ladder, and the
	first own-trained arm to pass both release-gate legs.

	## Results

	All numbers from the OpenCodifier evaluation records
	([BENCHMARKS.md](https://github.com/aliasfoxkde/OpenCodifier/blob/main/docs/BENCHMARKS.md),
	TRAINING.md §9.9.1). Public 231-item JevBench split, deterministic
	readout, fp16, single V100.

	\| metric \| value \|
	\|---\|---\|
	\| JevBench-231 accuracy \| 0.6840 (publish bar 0.6494 — clear) \|
	\| Internal holdout suite \| 0.8083 (gate ≥ 0.75 — GATE_PASS; seed-replicated 0.8000) \|
	\| Raw board ECE \| 0.207 \|
	\| Holdout-fitted temperature (T=3.362, analysis-only on board) \| ECE 0.207 → 0.127 \|
	\| Auto-decidable @5% risk \| 0.100 (23/231) \|
	\| Brier \| 0.504 \|
	\| p50 latency \| 0.58 s \|

	Per-family shape: routing / tool-selection / ordinal families at 1.00;
	relational/compositional families are the weakness (multi_hop 0.389,
	judge_hard 0.412, long_policy 0.368). The board is lost on compositional
	families, not on routing — the candidate lever is relational-heavy
	soft-label data, not parameters.

	## Training

	- Base: Qwen3.5-2B, LoRA verdict-slot readout
	- Corpus: merged-v3 (173,452 records; composition and join rates in
	TRAINING.md). The corpus itself is not released with this adapter.
	- Schedule: 11,009 steps, single V100 (T5500), fp16
	- Calibration: temperature T=3.362 fitted on a labelled holdout
	(holdout ECE 0.179 → 0.117); artifact ships in the OpenCodifier repo
	at `calibration/e1e-qwen3.5-2b-holdout.json`

	## Intended use

	Typed multiple-choice decisions (routing, tool selection, ordinal
	grading) where calibrated token-level probabilities — not free text —
	are the product. Pairs with the OpenCodifier engine's confidence gate:
	low-confidence reads abstain or escalate to a stronger rung.

	## Out of scope

	Free-form generation; the base model's general chat ability is not
	preserved or claimed. Not evaluated for safety of generated content —
	the adapter is a readout head, not a chat model.

	## How to use

	```python
	from peft import PeftModel
	from transformers import AutoModelForCausalLM, AutoTokenizer

	base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-2B", torch_dtype="float16")
	model = PeftModel.from_pretrained(base, "TaskWizerAI/opencodifier-e1e-2b")
	```

	Scores come from label-token log-probs at the answer position; see the
	OpenCodifier repo for the readout harness and the Jev adapter wire shape.

	## License

	Apache-2.0, matching the OpenCodifier project.

	## Citation

	```bibtex
	@software{opencodifier_e1e_2026,
	title = {OpenCodifier E1-E: a gate-passing 2B decision-model LoRA},
	author = {Kinney, Michael},
	year = {2026},
	url = {https://github.com/aliasfoxkde/OpenCodifier}
	}
	```