GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
openevo-recovery
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
openevo-recovery
Model Tree
Qwen/Qwen3-1.7B
Input Modalities
Output Modalities
Supported Functionality
本仓库是 Hugging Face 上的 模型仓库 openevo-recovery/openevo-minimax-20260903-qwen3-1p7b-opsd-lora。这段说明只提供双语导航，不修改原始模型、数据、实验结论或许可证。具体用途、身份、版本、限制及恢复方式，以本仓库保留的原始技术说明、Manifest 和源项目权威记录为准。
This is the Hugging Face model repository openevo-recovery/openevo-minimax-20260903-qwen3-1p7b-opsd-lora. This is a bilingual navigation note only; it does not change original model/data bytes, experiment findings, or licenses. For purpose, identity, version, limitations, and recovery, consult the preserved original technical documentation, manifests, and source-project authority.
这是历史 MiniMax 教师辅助 LoRA 的公开模型权重。额外 9 个中间 checkpoint 可参见 checkpoint 列表；实验分析、原始轨迹与内部记录不公开。详情见 中文说明。
This is an intermediate research checkpoint, not an ideal/final model, not a published benchmark claim, and not the MiniMax-M3 base model.
Qwen/Qwen3-1.7B.3e80e79b73c629cb305d31c9f7fa1c630b514c867d63f1cd1cf25b33532177ea.Apache-2.0. Include the upstream Qwen license and notices. Teacher-generated analysis text, raw rollouts, private experiment analysis, optimizer state, replay, credentials, and internal diagnostic records are not included. The product name MiniMax is used only to identify the teacher model; this release is not affiliated with or endorsed by MiniMax.
This is a PEFT LoRA adapter, not standalone base-model weights. Load the corresponding Qwen base model separately and apply the adapter with PEFT. Compatibility with the original historical runtime remains subject to independent verification.