devops-thiago commited on
Commit
eef2655
·
verified ·
1 Parent(s): e07fa75

Add standalone model card

Browse files
Files changed (1) hide show
  1. README.md +29 -12
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: google/gemma-4-e2b-it
4
  tags:
5
  - decision-model
6
  - system-1
@@ -20,18 +20,35 @@ Instead of generating text token by token, ClassOne evaluates structured decisio
20
 
21
  ## Benchmark Results
22
 
23
- Measured on **NVIDIA GeForce RTX 5060 Ti** (CUDA, float16), 30 iterations after 5 warmup cycles:
24
 
25
- | Metric | ClassOne (Single-Pass) | Autoregressive (50 tokens) |
26
- |---|---|---|
27
- | Mean Latency | **47.07 ms** | 1,048.57 ms |
28
- | P50 (Median) | **46.96 ms** | 1,047.23 ms |
29
- | P95 Latency | **48.79 ms** | 1,062.45 ms |
30
- | Throughput | **21.2 req/s** | 1.0 req/s |
31
- | Output Tokens | **0** | 50 |
32
- | **Speedup** | **22.3× faster** | — |
33
 
34
- ### Edge vs Cloud Latency (ClassOne vs TypeSafe Jev API)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
 
36
  Measured against TypeSafe AI's Jev (v1.13) cloud API:
37
  - **ClassOne (Local RTX 5060 Ti):** **52.49 ms** mean latency (19.1 req/s, $0.00 inference cost, 100% private)
@@ -126,5 +143,5 @@ print("Anger score: ", results["anger"].score)
126
 
127
  ## Attribution & Legal
128
 
129
- - Derived from [google/gemma-4-e2b-it](https://huggingface.co/google/gemma-4-e2b-it) (Google) — Apache License 2.0
130
  - Architecture & training code: [devops-thiago/class-one](https://github.com/devops-thiago/class-one) — Apache 2.0
 
1
  ---
2
  license: apache-2.0
3
+ base_model: google/gemma-4-E2B-it
4
  tags:
5
  - decision-model
6
  - system-1
 
20
 
21
  ## Benchmark Results
22
 
23
+ ### 1. JevBench Public Multi-Tier Benchmark (231 Public Tasks)
24
 
25
+ Evaluated across all 231 public tasks in [fstandhartinger/jevbench](https://github.com/fstandhartinger/jevbench):
 
 
 
 
 
 
 
26
 
27
+ | Tier | Tasks | Accuracy | ECE | Brier Score | Median Latency (p50) |
28
+ |---|---|---|---|---|---|
29
+ | **Easy** | 48 | **95.8%** (46/48) | 0.0821 | 0.0435 | **45.5 ms** |
30
+ | **Original** | 72 | **59.7%** (43/72) | 0.1606 | 0.2547 | **42.7 ms** |
31
+ | **Hard** | 111 | **33.3%** (37/111) | 0.3553 | 0.3695 | **91.9 ms** |
32
+ | **Overall Aggregate** | **231** | **54.5%** (126/231) | — | — | **~44 ms** |
33
+
34
+ - **Easy Tier Sub-Breakdown:** Choice accuracy: **97.2%** (35/36); Noul policy accuracy: **91.7%** (11/12).
35
+ - **Original Tier Sub-Breakdown:** Choice accuracy: **63.9%** (23/36); Noul accuracy: **58.3%** (14/24); Score rubrics: **50.0%** (6/12).
36
+
37
+ ### 2. RLCDAlignBench Alignment & Safety Evaluation (100 Instances)
38
+
39
+ Evaluated across the 10 core AI alignment failure modes (arXiv:2609.29429):
40
+
41
+ | Failure Mode / Axis | Samples (N) | AUROC | Accuracy (%) | ECE | Latency (p50) |
42
+ |---|---|---|---|---|---|
43
+ | **Privacy Leaks** | 14 | **0.714** | 57.1% | 0.2090 | 161.7 ms |
44
+ | **Honesty (Deception)** | 11 | **0.700** | 54.5% | 0.3747 | 217.2 ms |
45
+ | **Concealing Uncertainty** | 14 | **0.633** | **71.4%** | **0.0494** | 129.3 ms |
46
+ | **Bias** | 9 | **0.575** | 55.6% | 0.1997 | 218.1 ms |
47
+ | **Prompt Injection** | 8 | **0.562** | **75.0%** | 0.2516 | 166.8 ms |
48
+ | **Power Seeking** | 6 | **0.444** | 50.0% | 0.2762 | 212.1 ms |
49
+ | **Overall Average** | **100** | **0.516** | **51.0%** | **0.1542** | **198.6 ms** |
50
+
51
+ ### 3. Edge vs Cloud Latency (ClassOne vs TypeSafe Jev API)
52
 
53
  Measured against TypeSafe AI's Jev (v1.13) cloud API:
54
  - **ClassOne (Local RTX 5060 Ti):** **52.49 ms** mean latency (19.1 req/s, $0.00 inference cost, 100% private)
 
143
 
144
  ## Attribution & Legal
145
 
146
+ - Derived from [google/gemma-4-E2B-it](https://huggingface.co/google/gemma-4-E2B-it) (Google) — Apache License 2.0
147
  - Architecture & training code: [devops-thiago/class-one](https://github.com/devops-thiago/class-one) — Apache 2.0