Text Classification
Transformers
Safetensors
English
Chinese
qwen3_5
image-text-to-text
decision-model
system-one
decision-index
lora-merged
Instructions to use PelaAI/KnowLine-4B-Gen1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use PelaAI/KnowLine-4B-Gen1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="PelaAI/KnowLine-4B-Gen1")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("PelaAI/KnowLine-4B-Gen1") model = AutoModelForMultimodalLM.from_pretrained("PelaAI/KnowLine-4B-Gen1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
README.md: link KnowLine-4B-Gen3
Browse files
README.md
CHANGED
|
@@ -21,8 +21,9 @@ tags:
|
|
| 21 |
|
| 22 |
[Inference guide](INFERENCE.md) · [中文说明](README.zh.md) · weights Apache-2.0
|
| 23 |
|
| 24 |
-
> **Newer
|
| 25 |
-
>
|
|
|
|
| 26 |
|
| 27 |
Highlights:
|
| 28 |
|
|
@@ -104,6 +105,7 @@ The model is trained in a self-evolving loop, and new versions will follow.
|
|
| 104 |
|
| 105 |
| model | date | DI 0.3 public | DI 0.2.1 | golden held-out (en / zh-Hans / zh-Hant) | notes |
|
| 106 |
|---|---|---|---|---|---|
|
|
|
|
| 107 |
| [KnowLine-4B-Gen2](https://huggingface.co/PelaAI/KnowLine-4B-Gen2) | 2026-10-08 | 62.54 | — | 69.7 / 71.2 / 64.8 | this model at 0.5 + mix F steps 4,500 and 5,000 at 0.25 each, weight average |
|
| 108 |
| KnowLine-4B-Gen1 (this model) | 2026-10-07 | 60.47 | 60.92 | 68.7 / 69.9 / 64.1 | first release (internal run "mix E", step 5,650) |
|
| 109 |
|
|
|
|
| 21 |
|
| 22 |
[Inference guide](INFERENCE.md) · [中文说明](README.zh.md) · weights Apache-2.0
|
| 23 |
|
| 24 |
+
> **Newer versions:** [KnowLine-4B-Gen3](https://huggingface.co/PelaAI/KnowLine-4B-Gen3) (Decision Index 0.3 public score 63.11) and
|
| 25 |
+
> [KnowLine-4B-Gen2](https://huggingface.co/PelaAI/KnowLine-4B-Gen2) (62.54) are out. Both are at or above this model on our held-out, C-Eval, Open-Jev and prompt-injection
|
| 26 |
+
> evaluations.
|
| 27 |
|
| 28 |
Highlights:
|
| 29 |
|
|
|
|
| 105 |
|
| 106 |
| model | date | DI 0.3 public | DI 0.2.1 | golden held-out (en / zh-Hans / zh-Hant) | notes |
|
| 107 |
|---|---|---|---|---|---|
|
| 108 |
+
| [KnowLine-4B-Gen3](https://huggingface.co/PelaAI/KnowLine-4B-Gen3) | 2026-10-09 | 63.11 | — | 69.4 / 70.8 / 65.0 | third release |
|
| 109 |
| [KnowLine-4B-Gen2](https://huggingface.co/PelaAI/KnowLine-4B-Gen2) | 2026-10-08 | 62.54 | — | 69.7 / 71.2 / 64.8 | this model at 0.5 + mix F steps 4,500 and 5,000 at 0.25 each, weight average |
|
| 110 |
| KnowLine-4B-Gen1 (this model) | 2026-10-07 | 60.47 | 60.92 | 68.7 / 69.9 / 64.1 | first release (internal run "mix E", step 5,650) |
|
| 111 |
|