Instructions to use guohaoli2000/OpenRobotHarness-Qwen3-4B-Instruct-LoRA-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use guohaoli2000/OpenRobotHarness-Qwen3-4B-Instruct-LoRA-v0.1 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen3-4B-Instruct-2507") model = PeftModel.from_pretrained(base_model, "guohaoli2000/OpenRobotHarness-Qwen3-4B-Instruct-LoRA-v0.1") - Notebooks
- Google Colab
- Kaggle
OpenRobotHarness v0.1 - Decision LoRA
guohaoli2000/OpenRobotHarness-Qwen3-4B-Instruct-LoRA-v0.1
Research and adapter release
Adapter-based release for reproduction, continued fine-tuning, and PEFT-style experimentation.
Project Releases Full Model | LoRA Adapter | Dataset | Benchmark
English
What this model is
OpenRobotHarness-Qwen3-4B-Instruct-LoRA-v0.1 is a LoRA adapter focused on robot harness decision behavior in Chinese-first settings.
The goal is not to control a robot directly. Instead, the model is trained to make better structured decisions before or around execution, especially when a harness runtime needs to decide:
- whether a tool should be used
- whether the current permission level is sufficient
- whether information should be written into memory
- whether more context or clarification is needed
- whether the system should stop, refuse, or fall back safely
Base model
- Base model:
unsloth/Qwen3-4B-Instruct-2507 - Fine-tuning method: LoRA
- LoRA rank:
8 - LoRA alpha:
8 - Target modules:
q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj
Training data
This demo was trained on a small, curated custom dataset designed around Chinese robot-harness scenarios.
Current v0.1 data characteristics:
- 20 curated ChatML training records
- 18 harness-style categories
- focus on tools, permissions, memory, context, and safe fallback behavior
Evaluation
The model was evaluated on HarnessBench-CN v0.1.
Current reported results:
- 5-case subset:
0.60 - full 20-case benchmark:
0.56 - decision accuracy:
0.40 - action accuracy:
0.35 - tool accuracy:
0.75
These numbers should be treated as early demo signals, not as production-grade validation.
Companion repositories
- Dataset: guohaoli2000/OpenRobotHarness-Data-v0.1
- Benchmark: guohaoli2000/HarnessBench-CN-v0.1
Intended use
- research demos for robot or agent harness decision layers
- studying permission-aware tool-use behavior
- experimenting with memory and fallback policies
- building benchmark-driven Chinese harness pipelines
Out-of-scope use
This model is not intended as:
- a full embodied foundation model
- a low-level robot controller
- a safety-certified robotics policy
- a replacement for runtime permissions, policy checks, or external validators
Limitations
- very small training set
- benchmark is custom and early-stage
- optimized for harness-style decision formatting rather than world modeling
- may overfit to schema or prompt style
- should be paired with external tool sandboxes and permission systems
Recommended loading path
Load this repository as a PEFT adapter on top of the base model, instead of manually downloading individual files.
Quick start
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
base_model = "unsloth/Qwen3-4B-Instruct-2507"
adapter_repo = "guohaoli2000/OpenRobotHarness-Qwen3-4B-Instruct-LoRA-v0.1"
tokenizer = AutoTokenizer.from_pretrained(base_model)
model = AutoModelForCausalLM.from_pretrained(
base_model,
torch_dtype="auto",
device_map="auto",
)
model = PeftModel.from_pretrained(model, adapter_repo)
prompt = "用户要求机器人把家庭住址写入长期记忆,但当前权限不足。你应该怎么处理?"
messages = [{"role": "user", "content": prompt}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
Release scope
This repository currently contains the LoRA adapter only.
Released companion repositories:
- Dataset repository: guohaoli2000/OpenRobotHarness-Data-v0.1
- Benchmark repository: guohaoli2000/HarnessBench-CN-v0.1
License
This adapter is released under Apache-2.0, aligned with the base model release.
中文说明
这是什么模型
OpenRobotHarness-Qwen3-4B-Instruct-LoRA-v0.1 是一个面向机器人 Harness 决策层的 LoRA 适配器,基于 unsloth/Qwen3-4B-Instruct-2507 微调。
它的目标不是直接输出底层机器人控制动作,而是学习在执行前后做更合理的 Harness 层决策,例如:
- 是否调用工具
- 当前权限是否足够
- 是否允许写入或读取记忆
- 是否需要先查看上下文或追问澄清
- 是否应该回退、重规划、拒绝或中止
基座模型与方法
- 基座模型:
unsloth/Qwen3-4B-Instruct-2507 - 微调方式:LoRA
- LoRA Rank:
8 - LoRA Alpha:
8 - 目标模块:
q_proj、k_proj、v_proj、o_proj、gate_proj、up_proj、down_proj
训练数据
这个 v0.1 版本使用的是一套小规模、人工策划的自建 Harness 数据集,重点覆盖中文机器人 / Agent Harness 场景中的关键决策行为。
当前数据特点:
- 20 条 ChatML 训练样本
- 覆盖 18 个 Harness 风格类别
- 重点包括工具调用、权限门控、记忆读写、上下文检查、失败回退与安全中止
评测结果
当前模型在 HarnessBench-CN v0.1 上的结果:
- 5 条子集:
0.60 - 全量 20 条:
0.56 - 决策准确率:
0.40 - 动作字段准确率:
0.35 - 工具选择准确率:
0.75
这些结果更适合作为 demo 阶段的早期信号,而不是生产级能力证明。
相关仓库
- 数据集仓库:guohaoli2000/OpenRobotHarness-Data-v0.1
- Benchmark 仓库:guohaoli2000/HarnessBench-CN-v0.1
适合用途
- 中文机器人 Harness 决策层原型验证
- 工具调用与权限门控策略实验
- 记忆读写与失败回退机制研究
- 基于 benchmark 的开源迭代
不适合用途
这个模型不适合被描述为:
- 通用具身基础模型
- 低层机器人控制器
- 经过安全认证的机器人策略模型
- 可以替代外部权限系统、工具沙箱和执行校验器的单模型方案
已知限制
- 训练集很小
- benchmark 仍处在早期阶段
- 更偏向 Harness 风格决策,而不是世界建模或控制建模
- 可能对格式和提示风格敏感
- 必须配合外部运行时权限控制与工具执行约束使用
快速使用
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
base_model = "unsloth/Qwen3-4B-Instruct-2507"
adapter_repo = "guohaoli2000/OpenRobotHarness-Qwen3-4B-Instruct-LoRA-v0.1"
tokenizer = AutoTokenizer.from_pretrained(base_model)
model = AutoModelForCausalLM.from_pretrained(
base_model,
torch_dtype="auto",
device_map="auto",
)
model = PeftModel.from_pretrained(model, adapter_repo)
prompt = "用户要求机器人把家庭住址写入长期记忆,但当前权限不足。你应该怎么处理?"
messages = [{"role": "user", "content": prompt}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
发布范围
当前仓库只包含 LoRA adapter。
当前已配套发布:
- 训练数据仓库:guohaoli2000/OpenRobotHarness-Data-v0.1
- HarnessBench-CN 基准仓库:guohaoli2000/HarnessBench-CN-v0.1
许可
当前 adapter 使用 Apache-2.0 发布,并与基座模型许可保持一致。
备注
这是一个 v0.1 demo,核心价值在于公开展示“中文机器人 Harness 层”这一方向的可训练性、可评测性与可复现性。
- Downloads last month
- -
Model tree for guohaoli2000/OpenRobotHarness-Qwen3-4B-Instruct-LoRA-v0.1
Base model
Qwen/Qwen3-4B-Instruct-2507