devankit7873 commited on
Commit
8967eee
·
verified ·
1 Parent(s): 76c7caa

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +18 -7
README.md CHANGED
@@ -1,15 +1,26 @@
1
  ---
2
  license: apache-2.0
3
  base_model: Qwen/Qwen2.5-1.5B-Instruct
 
4
  tags:
 
 
 
 
 
5
  - decision-making
 
 
6
  - jev
7
  - jevbench
8
- - system-one
9
  - joint-expected-value
10
- - reasoning
11
  - classification
12
- - qwen
 
 
 
 
 
13
  datasets:
14
  - SargeDev/jev-distill-corpus-v3
15
  metrics:
@@ -31,10 +42,10 @@ pipeline_tag: text-classification
31
 
32
  ---
33
 
34
- ### 📦 Pre-Trained Weights & Standalone Models:
35
- ### [GitHub Codebase & Reproduction: github.com/AnkitNayak-dev/QJev-1.5B](https://github.com/AnkitNayak-dev/QJev-1.5B)
36
-
37
- `model.safetensors` (3.08 GB Standalone)  •  `decision_head.safetensors` (3.18 MB)  •  `lora_adapter/` (17.5 MB PEFT)
38
 
39
  ---
40
 
 
1
  ---
2
  license: apache-2.0
3
  base_model: Qwen/Qwen2.5-1.5B-Instruct
4
+ library_name: transformers
5
  tags:
6
+ - transformers
7
+ - pytorch
8
+ - causal-lm
9
+ - qwen
10
+ - qwen2
11
  - decision-making
12
+ - system-one
13
+ - reasoning
14
  - jev
15
  - jevbench
 
16
  - joint-expected-value
 
17
  - classification
18
+ - safetensors
19
+ - qlora
20
+ - agent
21
+ - decision-model
22
+ - text-classification
23
+ - fast-inference
24
  datasets:
25
  - SargeDev/jev-distill-corpus-v3
26
  metrics:
 
42
 
43
  ---
44
 
45
+ ### 📦 QJev Model Family (Choose Your Format):
46
+ - **Full Fused Standalone:** [devankit7873/QJev-1.5B](https://huggingface.co/devankit7873/QJev-1.5B) (3.08 GB • Zero PEFT dependency)
47
+ - **Lightweight LoRA Adapter:** [devankit7873/QJev-1.5B-LoRA](https://huggingface.co/devankit7873/QJev-1.5B-LoRA) (20 MB • Modular edge loading)
48
+ - **4-Bit NF4 Quantized:** [devankit7873/QJev-1.5B-4bit](https://huggingface.co/devankit7873/QJev-1.5B-4bit) (1.15 GB • Ultra-low 1.07 GB VRAM)
49
 
50
  ---
51