jodiox/olmo3-7b-zh-lora

基于 allenai/Olmo-3-7B-Instruct 的 LoRA SFT 微调版本。

训练配置

参数
基座模型 allenai/Olmo-3-7B-Instruct
量化 4bit (bitsandbytes)
LoRA 秩 r 16
LoRA alpha 16
学习率 1e-4
Epochs 2
数据集 jodiox/my-sft-dataset
训练框架 unsloth + TRL SFTTrainer

用法

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="jodiox/olmo3-7b-zh-lora",
    max_seq_length=2048,
    load_in_4bit=True,
)
FastLanguageModel.for_inference(model)
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for jodiox/olmo3-7b-zh-lora