mikuhhn1239
qwen3-8b-scene-segmentation-lora
Dedicated Endpoints
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Container
Run this model inference with full control and performance in your environment.
Get help setting up a custom Dedicated Endpoints.
Talk with our engineer to get a quote for reserved GPU instances with discounts.
README
License: apache-2.0任务
- 输入: 编号段落
[P1]...[P2]... - 输出:
{"boundaries": [N]}— N 为切分位置(在段落 N 之后切)
示例
markdown
输入:[P1] 下课铃响,教室里热闹起来。[P2] 她低头收拾书包。[P3] 我犹豫了一下,还是叫住了她。[P4] 十分钟后,我们并肩走在校门外的街道上。输出:{"boundaries": [3]} ← P3后切scene(教室→校门外)
加载
python
from transformers import AutoModelForCausalLMfrom peft import PeftModelbase = AutoModelForCausalLM.from_pretrained("mikuhhn1239/qwen3-8b-novel-base-sft",torch_dtype="auto", device_map="auto",)model = PeftModel.from_pretrained(base, "mikuhhn1239/qwen3-8b-scene-boundary-lora")
训练
markdown
基座: Qwen3-8B-Novel-Base-SFT (Stage1 全参 SFT, 72K 小说续写数据)方法: LoRA (r=64, α=128, dropout=0.05)数据: 350 条 (280 train / 35 val / 35 test),Clean 标注框架: transformers Trainer + PEFT优化器: AdamW (adamw_torch_fused), cosine schedule, warmup=5%epoch: 5 | LR: 1e-4 | batch: 1×16(accum) | bf16 | max_length: 4096
版本历史
| 版本 | 数据量 | epochs | LR | JSON解析 | 关键指标 |
|---|---|---|---|---|---|
| 零基座 (Qwen3-8B) | — | — | — | 2.9% | F1 0% |
| +Stage1 (全参SFT) | — | — | — | 0% | F1 0% |
| v1 | 82 | 3 | 2e-4 | 66.7% | F1 33.3% |
| v2 | ~150 | 3 | 2e-4 | 88.9% | F1 53.3% |
| v3 (LoRA) | 280 | 3 | 2e-4 | 97.1% | F1 19.6% |
| v3.1 (LoRA) | 280 | 5 | 1e-4 | 100% | F1 28.6% |
结论
- 零基座 / +Stage1 全 0%:不做 Agent SFT 就不会场景边界检测 ✅
- scene-boundary: 3→5 epochs 后 F1 从 19.6% → 28.6%(+9pp)
- v2 F1 53.3% 但任务定义不同(含原因输出),不可直接对比
Model provider
mikuhhn1239
Model tree
Base
mikuhhn1239/qwen3-8b-novel-base-sft
Adapter
this model
Modalities
Input
Text
Output
Text
Pricing
Dedicated Endpoints
View detailsSupported Functionality
Model APIs
Dedicated Endpoints
Container
More information