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

A LoRA adapter that turns 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 ladder, and the first own-trained arm to pass both release-gate legs.

Results

All numbers from the OpenCodifier evaluation records (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

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

@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}
}

Downloads last month: 18

Model tree for TaskWizerAI/opencodifier-e1e-2b

Base model

Qwen/Qwen3.5-2B-Base

Finetuned

Qwen/Qwen3.5-2B

Adapter

(287)

this model