Instructions to use PelaAI/KnowLine-35B-A3B-Gen1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use PelaAI/KnowLine-35B-A3B-Gen1.5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="PelaAI/KnowLine-35B-A3B-Gen1.5")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("PelaAI/KnowLine-35B-A3B-Gen1.5") model = AutoModelForMultimodalLM.from_pretrained("PelaAI/KnowLine-35B-A3B-Gen1.5", device_map="auto") - Notebooks
- Google Colab
- Kaggle
KnowLine-35B-A3B-Gen1.5
KnowLine-35B-A3B-Gen1 with a new way of serving it: the same weights, and a front end that reads short requests twice before it answers.
Inference guide Β· δΈζθ―΄ζ Β· weights Apache-2.0 Β· previous version: KnowLine-35B-A3B-Gen1
We raise the minor version when only inference changes and the major version (Gen) when the weights change. Every weight, config and tokenizer file of Gen1.5 is byte-identical to Gen1.
Highlights:
- Same weights, read twice. For a text-only request of up to 3,000 tokens, the front end writes the whole input a second time before the model answers. Nothing was trained; see What changed in Gen1.5.
- Decision Index 0.3 public suite: 70.72 (self-run, fresh full run), up from 69.49 for Gen1 with the same weights. The gains are concentrated in reasoning and inference over long inputs (knowledge and reasoning 52.5 β 55.0, language 71.2 β 72.9); short-text tasks are flat or slightly lower. See Comparison.
- Private scores: the board's full score comes from the maintainers' private run. Gen1 is listed at 61.20. Gen1.5 has the same weights as Gen1; its private scores will be produced by the maintainers' run.
- Other public benchmarks: C-Eval 88.1 (Gen1 on the same files: 87.7), JevBench / JevBench-hard 87.0 / 73.0 (85.7 / 70.3); see Evaluation.
- Calibration: the temperature folded into the weights, fitted on held-out data, is unchanged (T = 1.20). Computed with the board's method, ECE is about 0.03-0.04 (Gen1: 0.04-0.05) and the Brier score about 0.24-0.26 (Gen1: 0.25-0.27); see Calibration.
- Cost: about 1.56 times the prompt tokens of Gen1 on the Decision Index suite. One request at a time on one H20: 63.6 ms median and 101 ms mean, against 51 ms and 73 ms for Gen1 (our measurement, not the board's reference hardware); see INFERENCE.md.
- Images: unchanged. Requests with images are sent exactly as in Gen1, so Gen1's image results apply; see Images.
KnowLine is an independent model. It is not affiliated with, endorsed by, or derived from TypeSafe or Jev.
What it does
You send a state (text or a chat) and up to 64 typed questions: yes/no, choose one of k, or score on a rubric. The model answers every question with a probability distribution over its options:
- one forward pass per question, with no text generation;
- the output is the probability of each option's label token;
- existing Jev clients only need to change the base URL, and users of KnowLine-35B-A3B-Gen1 only need to change the model name, because the interface is the same.
| Base model | Qwen/Qwen3.5-35B-A3B (Apache-2.0): mixture of experts, 35B parameters in total, about 3B active per token |
| Weights | byte-identical to KnowLine-35B-A3B-Gen1: LoRA SFT (rank 32, alpha 64, language model only, including the routed experts), merged into bf16 weights (about 67 GB), with a readout temperature T = 1.20 folded into the final norm weight |
| Serving | serve_knowline.sh: SGLang converts the weights to FP8 at load (about 35 GB); knowline_server.py reads short requests twice (on by default; --no-read-twice gives the Gen1 prompts). We ran every evaluation with one server on one 96 GB H20; plan for at least 48 GB of GPU memory. |
| Languages | English, Simplified Chinese, Traditional Chinese |
Quickstart
pip install "sglang==0.5.21" "transformers==5.12.1" requests
bash serve_knowline.sh PelaAI/KnowLine-35B-A3B-Gen1.5 0 8080 # SGLang (FP8 at load) on :9080 + /v1/systemone on :8080
curl -s http://127.0.0.1:8080/v1/systemone -H 'Content-Type: application/json' -d '{
"model": "m",
"state": "Customer: my order arrived broken, I want my money back.",
"questions": {"refund": {"type": "noul", "instructions": "Should the agent offer a refund?"},
"tone": {"type": "choice", "instructions": "Customer tone?",
"criteria": {"angry": "Angry", "neutral": "Neutral", "happy": "Happy"}}}}'
- Front end:
knowline_server.pywithknowline_layout.pynext to it; together they depend only on transformers and requests. - Full settings: the exact settings used for our Decision Index run are in INFERENCE.md.
What changed in Gen1.5
- Read twice. Gen1 saw each request once: the state, then the instruction, the question and its options. Gen1.5 writes all of that a second time, introduced by the line "Read the same input again before answering:", and then reads the answer from the label token as before. The rule is mechanical: it applies to every text-only request of at most 3,000 tokens (94.6% of the Decision Index requests); longer requests and requests with images are sent as in Gen1.
- A likely reason. With causal attention, the first copy of a long state is read before the model knows the question; in the second copy every token can also attend to the first copy, question included. This fits where the gains are: reasoning and inference over long inputs.
- No training. The weights, the temperature and the label-token readout are those of Gen1. We checked the change on a fresh full run of the Decision Index public suite before release.
- Credit. The read-twice layout follows FlexDM (github.com/1000luca/FlexDM,
MIT); repeating the input goes back to RE2 (Xu et al., 2023,
arXiv:2309.06275).
knowline_layout.pyis our own implementation.
Comparison
Scores on the Decision Index. Since Decision Index 0.4, the board's full score is 60% private tests of the same skills and 40% private tasks from new domains; the public suite is shown but no longer counts. Gen1.5 has no board entry yet.
| model | size | DI 0.3 public | DI 0.4.1 full | source |
|---|---|---|---|---|
| KnowLine-35B-A3B-Gen1.5 | 35B-A3B | 70.72 | not yet scored | self-run, official kit |
| KnowLine-35B-A3B-Gen1 (same weights) | 35B-A3B | 69.49 | 61.20 | board |
| Fastino GLiDE V1.2 | β | 71.99 | 71.52 | board |
| Jeffan-31b-1710 | 31B | 73.13 | 69.75 | board |
| mammoth-1 | 27B | 75.18 | 68.87 | board |
| Perplexity Decider v1.2 | 27B | 67.74 | 67.98 | board |
| StartLux-Decision v1.1 27B | 27B | 72.88 | 67.92 | board |
| FlexDM Β· Gemma-4-31B | 31B | 63.63 | 67.56 | board |
| KnowLine-26B-A4B-Gen2 | 26B-A4B | 66.94 | 61.34 | board |
| Jev 1.14 | (API) | 60.70 | 60.24 | board |
| JEV-35B (Qwen3.5-35B-A3B) | 35B-A3B | 59.73 | 57.61 | board |
| Tern-35B-A3B | 35B-A3B | 59.01 | 56.62 | board |
Board rows from the board's data of 2026-10-21 (22:34 UTC, Decision Index 0.4.1).
Public-suite skill by area (DI 0.3, same weights):
| area | Gen1.5 | Gen1 |
|---|---|---|
| Knowledge & reasoning | 55.0 | 52.5 |
| Language | 72.9 | 71.2 |
| Retrieval & routing | 75.4 | 75.2 |
| Tools & agents | 88.2 | 88.1 |
| Arts & taste | 64.2 | 63.4 |
Releases
The model is trained in a self-evolving loop, and new versions will follow.
| model | date | DI 0.3 public | notes |
|---|---|---|---|
| KnowLine-35B-A3B-Gen1.5 (this model) | 2026-10-22 | 70.72 | Gen1 weights, read-twice serving |
| KnowLine-4B-Gen5 | 2026-10-21 | 65.67 | 4B, fifth release |
| KnowLine-26B-A4B-Gen2 | 2026-10-19 | 66.94 | 26B-A4B, second release |
| KnowLine-35B-A3B-Gen1 | 2026-10-12 | 69.49 | first 35B-A3B release |
Evaluation
All results are self-run and have not been verified by a third party. Every Gen1.5 number below was measured through the Gen1.5 front end (read twice on). Unless noted, the Gen1 numbers were measured again on the same files.
Other public benchmarks
| suite | 35B-A3B-Gen1.5 | 35B-A3B-Gen1 |
|---|---|---|
| C-Eval (4 categories, macro) | 88.1 | 87.7 |
| JevBench / JevBench-hard | 87.0 / 73.0 | 85.7 / 70.3 |
- In a paired test against Gen1, the differences on C-Eval and JevBench have p > 0.05.
Web operation (Mind2Web official test splits)
| split | Gen1.5 element selection | Gen1.5 operation (balanced) | Gen1 element selection | Gen1 operation (balanced) |
|---|---|---|---|---|
| test_task (Cross-Task) | 95.1 | 97.7 | 94.4 | 97.4 |
| test_website (Cross-Website) | 93.4 | 97.5 | 92.4 | 97.5 |
| test_domain (Cross-Domain) | 92.9 | 98.4 | 93.1 | 98.0 |
Within noise of Gen1 on all three splits (paired test, p β₯ 0.15); no request failed.
The task is to pick the target element from a candidate set: the target plus up to 5 other elements sampled from the page. This is easier than the original Mind2Web protocol, so do not compare these results with the Mind2Web leaderboard.
Images (zero-shot)
- Unchanged from Gen1: read twice applies only to text-only requests. A request with images is sent exactly as in Gen1, byte for byte, to the same weights, so Gen1's image results hold for Gen1.5 and we did not rerun them.
- Gen1's result: with the official kit, the Decision Index vision public suite gave 73.00 (12,210 rows, complete; self-run), published with Gen1's Decision Index results.
Calibration
Computed on the 0.3 public suite using the method described by the Decision Index board: each field is scored right or wrong, confidence is the probability of the chosen option, benchmarks are weighted equally, and 10 equal-width bins are used.
| metric | 35B-A3B-Gen1.5 | 35B-A3B-Gen1 |
|---|---|---|
| ECE (lower is better) | 0.03-0.04 | 0.04-0.05 |
| Brier score (lower is better) | 0.24-0.26 | 0.25-0.27 |
| Confidence β₯95% but wrong | 1.5% | 1.7% |
| Mean confidence / accuracy | 0.85-0.86 / 0.81-0.83 | 0.85-0.86 / 0.80-0.82 |
- Temperature in the weights: unchanged from Gen1: the final norm weight includes T = 1.20, fitted on held-out data, so every logit is divided by 1.20 before the softmax over the option labels.
- Why ranges: the board does not publish which benchmarks it uses for calibration, so we report ranges over the plausible benchmark sets, as for Gen1.
- Recommendation: if your use depends on probability thresholds, check calibration on your own data.
Disclosures
- Training data: the weights are those of Gen1, so the decontamination statement on the Gen1 card applies unchanged. The training data is not included in this repository.
- Public suite: the Decision Index public suite is public; the board's private tests may show a lower score.
Limitations
- Slower than Gen1: about 1.56 times the prompt tokens on the Decision Index suite; one request at a time on one H20,
63.6 ms median and 101 ms mean (Gen1: 51 ms and 73 ms), and 328 ms at the 95th percentile (Gen1: 174 ms). Use
--no-read-twiceif latency matters more than these gains. - Only short requests change: text-only requests over 3,000 tokens, and requests with images, are answered exactly as by Gen1.
- Short-text tasks: read twice does not help everywhere; a few short-text benchmarks are slightly lower than with Gen1.
- Everything else as Gen1: knowledge-heavy reasoning is still the weakest area (55.0, DI 0.3) and HLE remains at chance level; math answers come without step-by-step reasoning; prompt-injection attacks may still work, so keep untrusted text clearly delimited and in data fields of the state; the board's private tests may show a lower score than the public suite.
Citation
@misc{knowline35ba3bgen15,
title = {KnowLine-35B-A3B-Gen1.5: a 35B-A3B decision model served with read twice},
author = {PelaAI},
year = {2026},
url = {https://huggingface.co/PelaAI/KnowLine-35B-A3B-Gen1.5}
}
License
- Weights: Apache-2.0, the same as the base model.
- Code:
knowline_server.py,knowline_layout.pyandknowline_engine.pyare MIT (see the file headers).
- Downloads last month
- 833