jieying0729/olmo3-190m-zh-sft-v2

SFT(有监督微调)版本:基于 jieying0729/olmo3-190m-zh-full-4000, 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("jieying0729/olmo3-190m-zh-sft-v2")
tok = AutoTokenizer.from_pretrained("jieying0729/olmo3-190m-zh-sft-v2")
Downloads last month
5
Safetensors
Model size
0.2B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for jieying0729/olmo3-190m-zh-sft-v2

Unable to build the model tree, the base model loops to the model itself. Learn more.

Space using jieying0729/olmo3-190m-zh-sft-v2 1