Downloads · 30 days
23
20% of all-time downloads
openevo-recovery/openevo-h141-c0-exact-h140-sd-lora
openevo-h141-c0-exact-h140-sd-lora is a machine learning model from openevo-recovery. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as other.
本仓库是 Hugging Face 上的 模型仓库 openevo-recovery/openevo-h141-c0-exact-h140-sd-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。
Downloads · 30 days
23
20% of all-time downloads
All-time downloads
114
Public
Repo size
80.8 MB
Likes
0
Public
Click a slice to open those files.
.safetensors80.8 MB · 100%
From the Hugging Face model README
本仓库是 Hugging Face 上的 模型仓库 openevo-recovery/openevo-h141-c0-exact-h140-sd-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-h141-c0-exact-h140-sd-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 OpenEVO 跨平台实验资产的一部分。本段只补充统一身份与导航信息,不修改仓库已有模型、数据、checkpoint、trajectory 或历史科学语义。
miyuki17/openevo-h141-c0-exact-h140-sd-loraPUBLIC_MECHANISM_SCREEN_ARTIFACTmeasurement-invalid-mechanism-screentruepublicregistry-resolvedKEEP_STABLE_IDmykcs/openevo-experiment@bb57c88eb5de3036dee3ea9b095bc550dd6882c8mykcs/openevo-experiment@a1994980f16a922374f25442a599031825b2cf03命名和语言约定:repo、title、canonical ID 使用英文;README 默认中文。本“中文说明(默认)”是默认阅读入口,下方已有英文说明作为 English companion / historical detail 保留。若本段与 immutable publication receipt 或精确 remote revision/hash 冲突,以后者为准。
English: This block adds cross-platform identity metadata only. Existing artifact bytes and scientific claims are unchanged.
<!-- openevo-cross-platform-identity:end -->导航 / Navigation:OpenEvo WebShop 公开科研产物
本仓库归档 OpenEvo H1.41 WebShop magnitude screen 中 C0_exact_h140 臂的最终 PEFT/LoRA 适配器。
| 项目 | 值 |
|---|---|
| 活动 | 20260821-0141-h141-magnitude-screen |
| 臂 | C0_exact_h140 |
| 基础模型 | Qwen/Qwen2.5-7B-Instruct |
| 适配器文件 SHA-256 | 57cb6ade31f238af3788a771ecf82feb0eeed4c994f422c8391488606c6e734f |
| 评测 | 384/384 次正式尝试已完成 (evaluation-v5) |
| GitHub 证据 | https://github.com/mykcs/openevo-experiment/tree/main/docs/evidence/remote-runs/2026-08-21/h1.41 |
本适配器是 measurement-invalid 机制筛选产物,不是“exact-H1.40 updater 改善或损害 WebShop 性能”的证据。H1.41 活动的对账状态为 MEASUREMENT_INVALID:C0 acquisition 完整但点估计为 0;C0 与 C1 retention 同为 -0.065625;C1 有两个无效簇。因此不支持 magnitude-reset 因果声明、fresh-transfer 声明或 T2 声明。
此处仅发布适配器权重、训练来源与评测证据。
adapter_config.json — PEFT LoRA 配置adapter_model.safetensors — LoRA 权重(上方 SHA-256 已固定)openevo_sd_lora_state.json — OpenEvo SD-LoRA 状态/元数据README.md — 本文件from peft import PeftModel
import transformers
base = transformers.AutoModelForCausalLM.from_pretrained(
"Qwen/Qwen2.5-7B-Instruct",
torch_dtype="auto",
device_map="auto",
)
tokenizer = transformers.AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
model = PeftModel.from_pretrained(base, "miyuki17/openevo-h141-c0-exact-h140-sd-lora")
0.067254822729203931.56733753821283921.634592360942043f5657be6a5137114900fb816823c27c050fb48632f2f56f44c63b61044c3c5ec0b0b7acf6fa2e4fc7e817ff7271370d192a31835本适配器是 Qwen/Qwen2.5-7B-Instruct 的衍生作品,按 Qwen2.5 模型许可证分发。基础模型许可证及其限制适用。
从 OpenEvo 实验仓库发布:https://github.com/mykcs/openevo-experiment。
This repository archives the final PEFT/LoRA adapter for the C0_exact_h140 arm of the OpenEvo H1.41 magnitude screen on WebShop.
| Item | Value |
|---|---|
| Campaign | 20260821-0141-h141-magnitude-screen |
| Arm | C0_exact_h140 |
| Base model | Qwen/Qwen2.5-7B-Instruct |
| Adapter file SHA-256 | 57cb6ade31f238af3788a771ecf82feb0eeed4c994f422c8391488606c6e734f |
| Evaluation | 384/384 formal attempts completed (evaluation-v5) |
| GitHub evidence | https://github.com/mykcs/openevo-experiment/tree/main/docs/evidence/remote-runs/2026-08-21/h1.41 |
This adapter is a measurement-invalid mechanism screen artifact, not evidence that the exact-H1.40 updater improves or degrades WebShop performance. The H1.41 campaign reconciled as MEASUREMENT_INVALID: C0 acquisition had a complete but zero point estimate, C0 and C1 retention were identical at -0.065625, and C1 had two invalid clusters. Therefore no causal magnitude-reset claim, fresh-transfer claim, or T2 claim is supported.
Only the adapter weights, training provenance, and evaluation evidence are published here.
adapter_config.json — PEFT LoRA configurationadapter_model.safetensors — LoRA weights (SHA-256 pinned above)openevo_sd_lora_state.json — OpenEvo SD-LoRA state/metadataREADME.md — this filefrom peft import PeftModel
import transformers
base = transformers.AutoModelForCausalLM.from_pretrained(
"Qwen/Qwen2.5-7B-Instruct",
torch_dtype="auto",
device_map="auto",
)
tokenizer = transformers.AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
model = PeftModel.from_pretrained(base, "miyuki17/openevo-h141-c0-exact-h140-sd-lora")
0.06725482272920393 (both arms combined)1.56733753821283921.634592360942043f5657be6a5137114900fb816823c27c050fb48632f2f56f44c63b61044c3c5ec0b0b7acf6fa2e4fc7e817ff7271370d192a31835This adapter is a derivative work of Qwen/Qwen2.5-7B-Instruct and is distributed under the Qwen2.5 model license. The base model license and restrictions apply.
Published from the OpenEvo experiment repository: https://github.com/mykcs/openevo-experiment.