Instructions to use PelaAI/KnowLine-0.8B-Gen1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PelaAI/KnowLine-0.8B-Gen1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="PelaAI/KnowLine-0.8B-Gen1")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("PelaAI/KnowLine-0.8B-Gen1")
model = AutoModelForMultimodalLM.from_pretrained("PelaAI/KnowLine-0.8B-Gen1", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PelaAI/KnowLine-0.8B-Gen1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PelaAI/KnowLine-0.8B-Gen1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PelaAI/KnowLine-0.8B-Gen1",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/PelaAI/KnowLine-0.8B-Gen1

SGLang

How to use PelaAI/KnowLine-0.8B-Gen1 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 "PelaAI/KnowLine-0.8B-Gen1" \
    --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": "PelaAI/KnowLine-0.8B-Gen1",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "PelaAI/KnowLine-0.8B-Gen1" \
        --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": "PelaAI/KnowLine-0.8B-Gen1",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use PelaAI/KnowLine-0.8B-Gen1 with Docker Model Runner:
```
docker model run hf.co/PelaAI/KnowLine-0.8B-Gen1
```

KnowLine-0.8B-Gen1

Inference notes · 中文 · weights Apache-2.0 · released together with KnowLine-2B-Gen1 · also: KnowLine-9B-Gen1, KnowLine-4B-Gen5.5

KnowLine-0.8B-Gen1 is a 0.8B decision model based on Qwen3.5-0.8B. It maps a structured state and one or more typed questions to probabilities over the supplied options: choice, yes/no and ordered score questions. It reads the probability of each option label directly and does not generate free-form text when it answers. KnowLine is developed by PelaAI, a Japan-based team.

Highlights:

Decision Index 0.3 public suite: 44.51 (self-run, fresh full run with the files in this repository, read twice; 140,178 of 140,178 scoreable requests answered, no errors). The board's full score comes from the maintainers' private run and is not yet available for this model.
Small and fast: one request at a time on one H20, 24.6 ms median and 39.6 ms mean.
Other public benchmarks: C-Eval 56.3, JevBench / JevBench-hard 71.9 / 49.5; see Evaluation.
Calibrated probabilities: a readout temperature T = 1.54, fitted on held-out data, is folded into the weights. Computed with the board's method on the public suite, ECE is 0.008-0.012.
S1MB (English v1, local run): Task Avg 34.17 over 137 benchmarks (26,269 decisions, none failed or abstained).

What it does

choice questions with named options;
yes/no questions;
ordered score questions;
a readout temperature folded into the language-model norm, so the front end reads at temperature 1;
read twice for short text-only requests (up to 3,000 tokens read once).

Quickstart

Install PyTorch with CUDA, transformers and SGLang 0.5.21, then start the included front end:

bash serve_knowline.sh /path/to/KnowLine-0.8B-Gen1 0 8080

The front end serves /v1/systemone:

curl -s http://127.0.0.1:8080/v1/systemone \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "m",
    "state": "The parcel arrived damaged.",
    "questions": {
      "refund": {"type": "noul", "instructions": "Should the customer receive a refund?"},
      "route": {"type": "choice", "instructions": "Which team should handle this case?", "criteria": {"billing": "Payments and refunds", "support": "Technical troubleshooting"}}
    }
  }'

Front end: knowline_server.py, knowline_engine.py and knowline_layout.py implement the scoring front end used for every result below; temperatures.json must sit next to serve_knowline.sh.
Thinking off: the front end renders prompts with thinking turned off (enable_thinking=False). The Qwen3.5-0.8B chat template in this repository turns thinking on by default, so pass enable_thinking=False if you build prompts yourself.
Full settings: see INFERENCE.md.

How Gen1 was made

Base model: Qwen/Qwen3.5-0.8B.
Training: one epoch of LoRA SFT (rank 32, alpha 64, language-model linear layers only), merged into bf16 weights, at most 12,288 tokens per row. The released checkpoint is the end of training. Training examples include decision tasks written and labelled by LLM teachers.
Readout temperature: T = 1.54, fitted on held-out data and folded into model.language_model.norm.weight (see CALIBRATION.json). temperatures.json divides score-question logits by 0.6494 (= 1/1.54), so score questions are read at an effective temperature of 1.0.
Images: no image training; the vision tower is the base model's.

The training data is not included in this repository.

Comparison

Board entries of a similar size, from the Decision Index board snapshot multimodalart/jev-decision-index @ c130faf6 (data generated 2026-10-29 14:04 UTC). The board's DI 0.4.1 full score comes from the maintainers' private run.

model	size	DI 0.3 public	DI 0.4.1 full	source
KnowLine-0.8B-Gen1	0.8B	44.51	not yet scored	self-run, official kit
GLiClass v4 edge (0.4B)	0.4B	47.49	31.21	board
OneJev1.6-0.8B	0.9B	48.76	29.58	board
crystal-0.8b	0.9B	42.79	29.37	board
vLLM-SR vela3-fast (0.4B)	0.4B	50.36	29.27	board
StartLux-Decision v1.1 0.8B	0.9B	53.79	28.88	board

Evaluation

Full public Decision Index 0.3

Measured on 2026-10-29 with the files in this repository (bf16, read twice):

measurement	result
Public Decision Index	44.51
Public raw index	58.35
Requests / scoreable requests	140,620 / 140,178
Scoreable answers / errors / unsupported	140,178 / 0 / 0
One request at a time: median / mean / 95th percentile	24.6 / 39.6 / 117.3 ms

How the run was made: a fresh run of the 0.3 public suite with the official kit (commit 62d2f51), sent to four identical H20 servers started with serve_knowline.sh, 32 client shards. No request needed a retry and no input was truncated.
Hardware: H20 measurements, not the board's reference hardware.

Other public benchmarks

Both models of this release, on the same files and serving:

suite	2B-Gen1	0.8B-Gen1
C-Eval (4 categories, macro)	67.0	56.3
JevBench / JevBench-hard	77.5 / 55.9	71.9 / 49.5

S1MB (English v1)

A local run of the S1MB English v1 category (evaluator 9ad06fea, dataset 10bcb8c6) against this repository at commit b76c79d4, run ID knowline-08b-gen1-en-20261029-001: 137 benchmarks, 18,701 cases, 26,269 decisions, none failed or abstained. Task Avg 34.17 (choice 47.2, yes/no 37.1, score 18.3). This is the evaluator's task average, not a Borda rank or a leaderboard position.

Calibration

Computed on the 0.3 public suite with the method described by the Decision Index board (benchmarks weighted equally, confidence = probability of the chosen option, 10 equal-width bins); ranges cover the plausible benchmark sets, because the board does not publish which ones it uses.

metric	KnowLine-0.8B-Gen1
ECE (lower is better)	0.008-0.012
Brier score (lower is better)	0.41-0.43
Confidence ≥ 95% but wrong	0.3%
Mean confidence / accuracy	0.66-0.67 / 0.66-0.68

Recommendation: check calibration on your own data if your use depends on probability thresholds.

Disclosures

Decontamination: the complete training file was screened with standard and strict decontamination against the Decision Index public suite and the public benchmarks we report before training. This does not exclude exposure during the base model's pretraining.
Public suite: the Decision Index public suite is public; the board's private tests may show a lower score.

Limitations

Small model: a 0.8B model is well below our larger models on knowledge and reasoning-heavy questions (for example C-Eval 56.3 and JevBench-hard 49.5).
Planted instructions: put untrusted content in data fields of the state, not in the instructions, and keep it clearly delimited; the model can be steered by instructions planted in the input.
Calibration: probabilities are calibrated on average, not for every domain; check calibration on your own data.
Images: no image training; image use is zero-shot.
Thinking: use the included front end or pass enable_thinking=False; with the chat template's default the model would be prompted in thinking mode, which was not used in training.
Long requests: limited by the model and serving context; the front end does not truncate a request.
Not a chat assistant: it is a structured decision readout model.

Files and license

The weights and code are released under Apache 2.0. SHA256SUMS covers every file in this repository. The Qwen3.5-0.8B base model remains subject to its own license and terms.

Citation

@misc{knowline08bgen1,
  title        = {KnowLine-0.8B-Gen1},
  author       = {PelaAI},
  year         = {2026},
  howpublished = {Hugging Face model repository}
}

Downloads last month: 265

Safetensors

Model size

0.9B params

Tensor type

F32

BF16

Model tree for PelaAI/KnowLine-0.8B-Gen1

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B