samatv256 commited on
Commit
a2003a3
·
verified ·
1 Parent(s): cfa6715

Fix Hub library classification for custom mini-Jev model

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -1,6 +1,7 @@
1
  ---
2
  license: apache-2.0
3
  base_model: Qwen/Qwen3-0.6B
 
4
  tags:
5
  - mini-jev
6
  - decision-model
@@ -11,12 +12,11 @@ tags:
11
  - decision-making
12
  - finite-choice
13
  - qwen3
14
- - peft
15
  ---
16
 
17
  # mini-Jev Qwen3-0.6B - step 10,626
18
 
19
- mini-Jev is a **0.6B agentic decision model specialized for finite-choice tool and action selection**. Give it a state, a question, and candidate actions; it returns a probability for each candidate. It uses a Qwen3-0.6B backbone with an adapter and a compact decision head. Candidate scoring is permutation equivariant, and the model returns finite-choice probabilities rather than generated text or tool arguments.
20
 
21
  This is an **early 10,626-update checkpoint**. Training is planned through 50,000 updates; more training and broader decision supervision are coming. This interim release is not the final checkpoint.
22
 
 
1
  ---
2
  license: apache-2.0
3
  base_model: Qwen/Qwen3-0.6B
4
+ library_name: custom
5
  tags:
6
  - mini-jev
7
  - decision-model
 
12
  - decision-making
13
  - finite-choice
14
  - qwen3
 
15
  ---
16
 
17
  # mini-Jev Qwen3-0.6B - step 10,626
18
 
19
+ mini-Jev is a **0.6B agentic decision model specialized for finite-choice tool and action selection**. Give it a state, a question, and candidate actions; it returns a probability for each candidate. It uses a Qwen3-0.6B backbone with a PEFT/LoRA adapter and a compact decision head. Candidate scoring is permutation equivariant, and the model returns finite-choice probabilities rather than generated text or tool arguments.
20
 
21
  This is an **early 10,626-update checkpoint**. Training is planned through 50,000 updates; more training and broader decision supervision are coming. This interim release is not the final checkpoint.
22