Downloads · 30 days
9
15% of all-time downloads
olmo3-190m-zh-nano-sft
Fio3166/olmo3-190m-zh-nano-sft
olmo3-190m-zh-nano-sft is a machine learning model from Fio3166. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
SFT（有监督微调）版本：基于 Fio3166/olmo3-190m-zh-nano-continue， 使用对话格式数据进行微调，学习指令遵循能力。
All-time downloads
59
Public
Parameters
22M
44 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors44 MB · 92%
At a glance
- License
- apache-2.0
- Model type
- olmo3
- Access
- Public
- Created
- Jun 11, 2026
- Updated
- Jun 11, 2026
- SHA
- 3dadb8db
Base models
Model card
From the Hugging Face model README
Fio3166/olmo3-190m-zh-nano-sft
SFT（有监督微调）版本：基于 Fio3166/olmo3-190m-zh-nano-continue， 使用对话格式数据进行微调，学习指令遵循能力。
数据来源
- 训练数据：cmz1024/llm101-olmo3-zh-demo-data（来自 https://modelscope.cn/models/gongjy）
- 原始数据集：sft_t2t_mini.jsonl
训练配置
- LR：5e-05（低 LR 避免灾难性遗忘）
- Warmup：5.0%
- Max Seq Length：2048
用法
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("Fio3166/olmo3-190m-zh-nano-sft")
tok = AutoTokenizer.from_pretrained("Fio3166/olmo3-190m-zh-nano-sft")
- Type
- olmo3
- License
- apache-2.0
- Languages
- zh
- Created
- Jun 11, 2026
- Updated
- Jun 11, 2026