jieying0729/olmo3-190m-zh-full-4000-continue
持续预训练版本：基于 jieying0729/olmo3-190m-zh-full-4000（基础预训练 4000 步，loss 4.09）， 在 full_v31 数据上继续训练 200 步（loss 8.79 → 5.53）。
训练配置
- 数据：cmz1024/llm101-olmo3-zh-demo-data/continue/full_v31.bin
- LR：2e-4（低 LR 防止灾难性遗忘）
- Warmup：10%
用法
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("jieying0729/olmo3-190m-zh-full-4000-continue")
tok = AutoTokenizer.from_pretrained("jieying0729/olmo3-190m-zh-full-4000-continue")
- Downloads last month
- 2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for jieying0729/olmo3-190m-zh-full-4000-continue
Unable to build the model tree, the base model loops to the model itself. Learn more.