Text Classification
Transformers
Safetensors
English
Chinese
qwen3_5
image-text-to-text
decision-model
system-one
decision-index
lora-merged
model-soup
Instructions to use PelaAI/KnowLine-4B-Gen2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use PelaAI/KnowLine-4B-Gen2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="PelaAI/KnowLine-4B-Gen2")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("PelaAI/KnowLine-4B-Gen2") model = AutoModelForMultimodalLM.from_pretrained("PelaAI/KnowLine-4B-Gen2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
README.zh.md: link KnowLine-4B-Gen3
Browse files- README.zh.md +3 -0
README.zh.md
CHANGED
|
@@ -4,6 +4,8 @@
|
|
| 4 |
|
| 5 |
[推理说明](INFERENCE.md) · [English](README.md) · 权重 Apache-2.0 · 上一版:[KnowLine-4B-Gen1](https://huggingface.co/PelaAI/KnowLine-4B-Gen1)
|
| 6 |
|
|
|
|
|
|
|
| 7 |
亮点:
|
| 8 |
|
| 9 |
- **Decision Index 0.3 公开套件:62.54**(自测),比 Gen1(60.47)高 2.07。作为对照:Jev 1.13 为 57.96(榜单);榜单上 ≤5B 模型的最高公开分为 50.82,见[横向对比](#横向对比)。
|
|
@@ -91,6 +93,7 @@ curl -s http://127.0.0.1:8080/v1/systemone -H 'Content-Type: application/json' -
|
|
| 91 |
|
| 92 |
| 模型 | 日期 | DI 0.3 公开 | DI 0.2.1 | 黄金集留出(英 / 简 / 繁) | 说明 |
|
| 93 |
| --------------------- | ---------- | --------- | -------- | ------------------ | ---------------------------- |
|
|
|
|
| 94 |
| KnowLine-4B-Gen2(本模型) | 2026-10-08 | 62.54 | — | 69.7 / 71.2 / 64.8 | Gen1 占 0.5,mix F 第 4,500、5,000 步各占 0.25,权重平均 |
|
| 95 |
| [KnowLine-4B-Gen1](https://huggingface.co/PelaAI/KnowLine-4B-Gen1) | 2026-10-07 | 60.47 | 60.92 | 68.7 / 69.9 / 64.1 | 首次发布(内部运行 "mix E",第 5,650 步) |
|
| 96 |
|
|
|
|
| 4 |
|
| 5 |
[推理说明](INFERENCE.md) · [English](README.md) · 权重 Apache-2.0 · 上一版:[KnowLine-4B-Gen1](https://huggingface.co/PelaAI/KnowLine-4B-Gen1)
|
| 6 |
|
| 7 |
+
> **新版本**:[KnowLine-4B-Gen3](https://huggingface.co/PelaAI/KnowLine-4B-Gen3) 已发布:DI 0.3 公开分 63.11。
|
| 8 |
+
|
| 9 |
亮点:
|
| 10 |
|
| 11 |
- **Decision Index 0.3 公开套件:62.54**(自测),比 Gen1(60.47)高 2.07。作为对照:Jev 1.13 为 57.96(榜单);榜单上 ≤5B 模型的最高公开分为 50.82,见[横向对比](#横向对比)。
|
|
|
|
| 93 |
|
| 94 |
| 模型 | 日期 | DI 0.3 公开 | DI 0.2.1 | 黄金集留出(英 / 简 / 繁) | 说明 |
|
| 95 |
| --------------------- | ---------- | --------- | -------- | ------------------ | ---------------------------- |
|
| 96 |
+
| [KnowLine-4B-Gen3](https://huggingface.co/PelaAI/KnowLine-4B-Gen3) | 2026-10-09 | 63.11 | — | 69.4 / 70.8 / 65.0 | 第三版 |
|
| 97 |
| KnowLine-4B-Gen2(本模型) | 2026-10-08 | 62.54 | — | 69.7 / 71.2 / 64.8 | Gen1 占 0.5,mix F 第 4,500、5,000 步各占 0.25,权重平均 |
|
| 98 |
| [KnowLine-4B-Gen1](https://huggingface.co/PelaAI/KnowLine-4B-Gen1) | 2026-10-07 | 60.47 | 60.92 | 68.7 / 69.9 / 64.1 | 首次发布(内部运行 "mix E",第 5,650 步) |
|
| 99 |
|