Harness-R1

Model artifacts for Harness-R1 experiments. The repository separates the target agent from the Harness Engineer so that the two roles are not confused.

Directory	Role
`harness-r1/`	E0 Harness Engineer for the vanilla A0 target agent
`agent-sft-harness-r1/`	E1 Harness Engineer conditioned on A1 trajectories
`target-agent-sft/`	Direct Agent-SFT target model (A1), not a Harness Engineer

Loading

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "ShaoShuai0605/Harness-R1"
subfolder = "harness-r1"  # Or agent-sft-harness-r1 / target-agent-sft

tokenizer = AutoTokenizer.from_pretrained(
    repo,
    subfolder=subfolder,
    trust_remote_code=True,
)
model = AutoModelForCausalLM.from_pretrained(
    repo,
    subfolder=subfolder,
    trust_remote_code=True,
)

See the README inside each directory for its intended role.

Downloads last month: -; Downloads are not tracked for this model. How to track

Video Preview

Reinforcement Learning

Model tree for ShaoShuai0605/Harness-R1

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

(749)

this model

Quantizations

1 model