6shmqshy7q-dot/olmo3-190m-zh-nano-continue
持续预训练版本：基于 6shmqshy7q-dot/olmo3-190m-zh-nano， 在 42ailab/llm101-v3.1-data/nano_0.5B.bin 数据上继续训练。
训练配置
- 数据：42ailab/llm101-v3.1-data/nano_0.5B.bin (500M 中文 tokens)
- 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("6shmqshy7q-dot/olmo3-190m-zh-nano-continue")
tok = AutoTokenizer.from_pretrained("6shmqshy7q-dot/olmo3-190m-zh-nano-continue")
- Downloads last month
- 10
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for 6shmqshy7q-dot/olmo3-190m-zh-nano-continue
Unable to build the model tree, the base model loops to the model itself. Learn more.