Text Generation
PEFT
Safetensors
Chinese
qwen3
lora
narrative-parsing
novel-analysis
chinese-novels
conversational
Instructions to use mikuhhn1239/qwen3-8b-narrative-parsing-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use mikuhhn1239/qwen3-8b-narrative-parsing-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("mikuhhn1239/qwen3-8b-novel-base-sft") model = PeftModel.from_pretrained(base_model, "mikuhhn1239/qwen3-8b-narrative-parsing-lora") - Notebooks
- Google Colab
- Kaggle
v4: 扩标~1200条, acc 69.5%→72.8%(+3.3pp)
Browse files各类型: narration 82%, dialogue 70%, thought 62%, action 58%, scene_description 54%. 继续稳步提升, narration 已达实用水平
- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
adapter_config.json
CHANGED
|
@@ -30,13 +30,13 @@
|
|
| 30 |
"rank_pattern": {},
|
| 31 |
"revision": null,
|
| 32 |
"target_modules": [
|
| 33 |
-
"up_proj",
|
| 34 |
-
"v_proj",
|
| 35 |
-
"o_proj",
|
| 36 |
"k_proj",
|
| 37 |
"q_proj",
|
|
|
|
|
|
|
| 38 |
"gate_proj",
|
| 39 |
-
"down_proj"
|
|
|
|
| 40 |
],
|
| 41 |
"target_parameters": null,
|
| 42 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 30 |
"rank_pattern": {},
|
| 31 |
"revision": null,
|
| 32 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
| 33 |
"k_proj",
|
| 34 |
"q_proj",
|
| 35 |
+
"up_proj",
|
| 36 |
+
"v_proj",
|
| 37 |
"gate_proj",
|
| 38 |
+
"down_proj",
|
| 39 |
+
"o_proj"
|
| 40 |
],
|
| 41 |
"target_parameters": null,
|
| 42 |
"task_type": "CAUSAL_LM",
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 698419728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4db47e03a84b058a61f48395c4e19846c4c3b6da16545ef50f7d9ee4c8c84034
|
| 3 |
size 698419728
|