Hugging Face's logo

ShaoShuai0605
/
Harness-R1

Reinforcement Learning
Transformers
Safetensors
harness-r1
agent
Model card Files
xet
 Community
ShaoShuai0605 commited on
Commit
2b06337
·
verified ·
1 Parent(s): a96827d

Simplify model card

Browse files
Files changed (1) hide show
  1. README.md +9 -22
README.md CHANGED
@@ -8,33 +8,20 @@ tags:
8
  - reinforcement-learning
9
  ---
10
 
11
- # Harness-R1 Checkpoints
12
 
13
- This repository hosts the two **Harness-R1 harness-engineer** checkpoints reported in the paper main table (`Ours` block):
14
 
15
- | Subfolder | Paper row | Role |
16
- |---|---|---|
17
- | [`harness-r1-e0-iter143`](./harness-r1-e0-iter143) | **Harness-R1** | Engineer trained with identity-clean SFT + online RL on frozen vanilla Qwen3.5-9B (A0). Valid-selected checkpoint `iter143`. |
18
- | [`harness-r1-e1-iter495`](./harness-r1-e1-iter495) | **Agent SFT + Harness-R1** | Continued engineer RL (E0→E1) on the Agent-SFT target (A1). Valid-selected checkpoint `iter495`. |
19
-
20
- Both folders are full Hugging Face Transformers checkpoints (≈18GB each, single `model.safetensors`) derived from Qwen3.5-9B.
21
-
22
- ## Quick load
23
 
24
  ```python
25
  from transformers import AutoModelForCausalLM, AutoTokenizer
26
 
27
  repo = "ShaoShuai0605/Harness-R1"
28
- # main-table Harness-R1 engineer
29
- tok = AutoTokenizer.from_pretrained(repo, subfolder="harness-r1-e0-iter143", trust_remote_code=True)
30
- model = AutoModelForCausalLM.from_pretrained(repo, subfolder="harness-r1-e0-iter143", trust_remote_code=True)
31
  ```
32
-
33
- For the Agent-SFT + Harness-R1 engineer, use `subfolder="harness-r1-e1-iter495"`.
34
-
35
- Code and evaluation harness: see the companion open-source release for Harness-R1.
36
-
37
- ## Notes
38
-
39
- - These checkpoints are **harness engineers** (patch generators), not the frozen target agents used at evaluation time.
40
- - Serving for tool-call / patch generation should follow the project’s Qwen3.5 engineer protocol (`enable_thinking` as used in the corresponding eval configs).
 
8
  - reinforcement-learning
9
  ---
10
 
11
+ # Harness-R1
12
 
13
+ Harness-engineer checkpoints from the paper main table.
14
 
15
+ | Subfolder | Paper row |
16
+ |---|---|
17
+ | [`harness-r1-e0-iter143`](./harness-r1-e0-iter143) | Harness-R1 |
18
+ | [`harness-r1-e1-iter495`](./harness-r1-e1-iter495) | Agent SFT + Harness-R1 |
 
 
 
 
19
 
20
  ```python
21
  from transformers import AutoModelForCausalLM, AutoTokenizer
22
 
23
  repo = "ShaoShuai0605/Harness-R1"
24
+ subfolder = "harness-r1-e0-iter143" # or harness-r1-e1-iter495
25
+ tok = AutoTokenizer.from_pretrained(repo, subfolder=subfolder, trust_remote_code=True)
26
+ model = AutoModelForCausalLM.from_pretrained(repo, subfolder=subfolder, trust_remote_code=True)
27
  ```