Downloads · 30 days
5
9% of all-time downloads
olmo3-190m-zh-full
livingworld/olmo3-190m-zh-full
olmo3-190m-zh-full is a machine learning model from livingworld. 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.
为零基础 AI 大模型研发训练营（llm001）L04 Full 模型（190M 参数，20 步测试训练）。
All-time downloads
53
Public
Parameters
187M
1.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors374 MB · 99%
At a glance
- License
- apache-2.0
- Model type
- olmo3
- Access
- Public
- Created
- Jun 6, 2026
- Updated
- Sep 30, 2026
- SHA
- 6a9b9faf
Model card
From the Hugging Face model README
OLMo3-190M-zh-full
为零基础 AI 大模型研发训练营（llm001）L04 Full 模型（190M 参数，20 步测试训练）。
模型配置
- hidden_size: 768, num_layers: 12, num_heads: 12, intermediate_size: 3072
- vocab_size: 48000, sliding_window: 4096
训练配置
- 数据：cmz1024/llm101-olmo3-zh-demo-data (500M tokens)
- 训练：H100, max_steps=20, bs=16×8=128, lr=5e-4, bf16
用法
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("livingworld/olmo3-190m-zh-full")
tok = AutoTokenizer.from_pretrained("livingworld/olmo3-190m-zh-full")
- Type
- olmo3
- License
- apache-2.0
- Languages
- zh
- Created
- Jun 6, 2026
- Updated
- Sep 30, 2026