Add link to paper

#1
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +10 -6
README.md CHANGED
@@ -1,13 +1,13 @@
1
  ---
2
- language:
3
- - en
4
- license: apache-2.0
5
- library_name: transformers
6
- pipeline_tag: text-generation
7
  base_model:
8
  - Qwen/Qwen3.5-9B
9
  datasets:
10
  - beita6969/SkillFlow-Dataset
 
 
 
 
 
11
  tags:
12
  - skillflow
13
  - agentic-ai
@@ -20,6 +20,10 @@ tags:
20
 
21
  This repository contains the merged SkillFlow Supervisor model weights.
22
 
 
 
 
 
23
  ## Source
24
 
25
  - Code: https://github.com/beita6969/SkillFlow
@@ -36,4 +40,4 @@ This repository contains the merged SkillFlow Supervisor model weights.
36
  - Target modules: `q_proj`, `k_proj`, `v_proj`, `o_proj`
37
  - Merge dtype: bfloat16
38
 
39
- The training-time backward policy adapter is not merged into this inference model.
 
1
  ---
 
 
 
 
 
2
  base_model:
3
  - Qwen/Qwen3.5-9B
4
  datasets:
5
  - beita6969/SkillFlow-Dataset
6
+ language:
7
+ - en
8
+ library_name: transformers
9
+ license: apache-2.0
10
+ pipeline_tag: text-generation
11
  tags:
12
  - skillflow
13
  - agentic-ai
 
20
 
21
  This repository contains the merged SkillFlow Supervisor model weights.
22
 
23
+ ## Paper
24
+
25
+ - [SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration](https://huggingface.co/papers/2605.14089)
26
+
27
  ## Source
28
 
29
  - Code: https://github.com/beita6969/SkillFlow
 
40
  - Target modules: `q_proj`, `k_proj`, `v_proj`, `o_proj`
41
  - Merge dtype: bfloat16
42
 
43
+ The training-time backward policy adapter is not merged into this inference model.