Text Classification
Transformers
Safetensors
PyTorch
qwen2
text-generation
causal-lm
qwen
decision-making
system-one
reasoning
jev
jevbench
joint-expected-value
classification
qlora
agent
decision-model
fast-inference
text-embeddings-inference
Instructions to use devankit7873/QJev-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use devankit7873/QJev-1.5B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="devankit7873/QJev-1.5B")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("devankit7873/QJev-1.5B") model = AutoModelForCausalLM.from_pretrained("devankit7873/QJev-1.5B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
docs: sync polished README with Phase 3 benchmarks and multi-engine serving
Browse files
README.md
CHANGED
|
@@ -1,349 +1,331 @@
|
|
| 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:
|
| 27 |
-
- accuracy
|
| 28 |
-
- tvd
|
| 29 |
-
- kl_divergence
|
| 30 |
-
pipeline_tag: text-classification
|
| 31 |
-
---
|
| 32 |
-
|
| 33 |
-
<div align="center">
|
| 34 |
-
|
| 35 |
-
# β‘ QJev-1.5B:
|
| 36 |
-
###
|
| 37 |
-
|
| 38 |
-
[](https://github.com/AnkitNayak-dev/QJev-1.5B)
|
| 40 |
-
[. Metamorphic benchmarking powered by JevBench.
|
|
|
|
| 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:
|
| 27 |
+
- accuracy
|
| 28 |
+
- tvd
|
| 29 |
+
- kl_divergence
|
| 30 |
+
pipeline_tag: text-classification
|
| 31 |
+
---
|
| 32 |
+
|
| 33 |
+
<div align="center">
|
| 34 |
+
|
| 35 |
+
# β‘ QJev-1.5B: High-Speed System 1 JEV Decision Model
|
| 36 |
+
### Single-Pass Real-Time Decision Engine (~31 ms Forward Pass β’ Ranked #1 Sub-2B Model)
|
| 37 |
+
|
| 38 |
+
[](https://huggingface.co/devankit7873/QJev-1.5B)
|
| 39 |
+
[](https://github.com/AnkitNayak-dev/QJev-1.5B)
|
| 40 |
+
[-8A2BE2?style=for-the-badge)](https://benchmarkheaven.com/jev-models)
|
| 41 |
+
[-blue?style=for-the-badge)](https://benchmarkheaven.com/jev-models)
|
| 42 |
+
[](LICENSE)
|
| 43 |
+
|
| 44 |
+
---
|
| 45 |
+
|
| 46 |
+
### π³ Hugging Face Model Tree & Flavors:
|
| 47 |
+
```
|
| 48 |
+
Qwen/Qwen2.5-1.5B-Instruct (Root Base)
|
| 49 |
+
βββ β‘ devankit7873/QJev-1.5B (Flagship Fused 16-bit β’ 3.08 GB β’ Zero PEFT dependency)
|
| 50 |
+
βββ π devankit7873/QJev-1.5B-LoRA (PEFT Adapter β’ 20 MB β’ Modular edge loading)
|
| 51 |
+
βββ ποΈ devankit7873/QJev-1.5B-4bit (NF4 Quantized β’ 1.15 GB β’ 1.07 GB VRAM)
|
| 52 |
+
```
|
| 53 |
+
|
| 54 |
+
[News](#-news) β’ [Overview](#-overview-system-1-decision-paradigm) β’ [Leaderboard & Benchmarks](#-official-benchmarkheaven--jevbench-results) β’ [Quickstart](#-quickstart--usage) β’ [Multi-Engine Serving](#-multi-engine-inference-deployment) β’ [Architecture](#-model-architecture) β’ [Repo Structure](#-repository-structure) β’ [Citation](#-citation)
|
| 55 |
+
|
| 56 |
+
</div>
|
| 57 |
+
|
| 58 |
+
---
|
| 59 |
+
|
| 60 |
+
## π’ News
|
| 61 |
+
* **[2026-11-17] π― Phase 3 Consistency Release & Multi-Engine Serving:**
|
| 62 |
+
- Trained with cross-format symmetric consistency loss, boosting official **JevBench strict tolerance (0.05) score from 58.67% to 62.53%** (+3.86% overall, +15.2% on choice conditioning).
|
| 63 |
+
- Officially ranks as the **#1 decision model in the sub-2B tier**, outperforming multiple 4B baselines on [BenchmarkHeaven](https://benchmarkheaven.com/jev-models).
|
| 64 |
+
- Shipped native deployment support for **vLLM**, **Ollama (`Modelfile`)**, **llama.cpp (GGUF)**, and **production FastAPI (`serve.py`)**.
|
| 65 |
+
* **[2026-11-16] π Initial Release:**
|
| 66 |
+
- Full QLoRA joint training across all 655,806 distillation samples of `SargeDev/jev-distill-corpus-v3`.
|
| 67 |
+
- Achieves **71.50% relaxed metamorphic score** in **3.4 GB VRAM at ~31 ms per decision**.
|
| 68 |
+
|
| 69 |
+
---
|
| 70 |
+
|
| 71 |
+
## π‘ Overview: System 1 Decision Paradigm
|
| 72 |
+
|
| 73 |
+
Traditional LLMs make decisions through slow, non-deterministic token-by-token autoregressive generation (e.g. generating `"Option A"` over 300β600 ms).
|
| 74 |
+
|
| 75 |
+
**`QJev-1.5B`** introduces a **System 1 Decision Architecture**:
|
| 76 |
+
1. Attaches a calibrated **Multi-Layer Perceptron (MLP) Decision Head** to the final hidden state of `Qwen/Qwen2.5-1.5B-Instruct`.
|
| 77 |
+
2. Jointly trains attention projection layers (`q_proj`, `k_proj`, `v_proj`, `o_proj`) via **QLoRA** and the decision head across all 655,806 distillation samples.
|
| 78 |
+
3. In Phase 3, fine-tunes with soft target KL-divergence consistency loss across multiple-choice, boolean probes, and permutation groups.
|
| 79 |
+
4. Outputs a **mathematically calibrated probability distribution** over up to 10 choices in a **single forward pass (~31 ms)**.
|
| 80 |
+
|
| 81 |
+
---
|
| 82 |
+
|
| 83 |
+
## π Official BenchmarkHeaven & JevBench Results
|
| 84 |
+
|
| 85 |
+
Evaluated against the official **JevBench** test harness (`jevbench-mini`, 240 cases, 50 scored metamorphic relations, 1,468 trials):
|
| 86 |
+
|
| 87 |
+
### 1. Leaderboard Placement (BenchmarkHeaven JEV Leaderboard)
|
| 88 |
+
|
| 89 |
+
Under the official BenchmarkHeaven standard (**strict tolerance = 0.05**):
|
| 90 |
+
|
| 91 |
+
| Model | Parameters | Benchmark Score (tol=0.05) | Rank / Category | Latency | VRAM Footprint |
|
| 92 |
+
| :--- | :---: | :---: | :---: | :---: | :---: |
|
| 93 |
+
| `EXAONE-1.2B` | 1.2B | 47.7% | Sub-2B | ~25 ms | ~2.8 GB |
|
| 94 |
+
| `SargeDev/jev-gate-student-b` | 0.49B | 50.2% | Sub-2B (Binary Only) | ~23 ms | ~1.5 GB |
|
| 95 |
+
| `decision-2b` | 2.0B | 54.8% | 2B Tier | ~40 ms | ~4.5 GB |
|
| 96 |
+
| `pjev-2b` | 2.0B | 56.5% | 2B Tier | ~38 ms | ~4.4 GB |
|
| 97 |
+
| **`QJev-1.5B` (Ours, Phase 3)** | **1.54B** | **62.53%** | **π #1 Sub-2B (Beats 4B)** | **~31 ms** | **~3.4 GB (1.07 GB in 4-bit)** |
|
| 98 |
+
| `jiwo-4b` | 4.0B | 60.2% | 4B Tier | ~65 ms | ~8.8 GB |
|
| 99 |
+
| `decision-4b-v12` | 4.0B | 60.4% | 4B Tier | ~62 ms | ~8.5 GB |
|
| 100 |
+
| `autotrust/JEV-9B` | 9.0B | 72.0% | 9B Tier | ~85 ms | ~18.5 GB |
|
| 101 |
+
| `autotrust/JEV-27B` | 27.0B | 76.5% | Server Tier | ~220 ms | ~55.0 GB |
|
| 102 |
+
|
| 103 |
+
> **Note on Evaluation Tolerances:**
|
| 104 |
+
> - **Official Strict (`tol = 0.05`):** **62.53%** (Official score reported on BenchmarkHeaven public leaderboard).
|
| 105 |
+
> - **Relaxed Exploration (`tol = 0.10`):** **71.50%** (Lenient consistency threshold).
|
| 106 |
+
|
| 107 |
+
### 2. Breakdown Across Metamorphic Dimensions
|
| 108 |
+
|
| 109 |
+
| Dimension | Baseline (Pre-Consistency) | QJev-1.5B (Phase 3 Consistency) | Gain | Practical Meaning |
|
| 110 |
+
| :--- | :---: | :---: | :---: | :--- |
|
| 111 |
+
| **`BAT.isolation`** | **100.0%** | **100.0%** | **0.0%** | Batching independence (Zero cross-talk between batch items) |
|
| 112 |
+
| **`REP.type`** | 77.1% | **83.3%** | **+6.2%** | Format coherence across multi-choice, boolean, and ordinal prompts |
|
| 113 |
+
| **`REP.invariance`** | 73.2% | **74.4%** | **+1.2%** | Immune to choice reordering and prompt syntax perturbations |
|
| 114 |
+
| **`LOG.bounds`** | 62.5% | **67.9%** | **+5.4%** | Strict adherence to probabilistic upper and lower bounds |
|
| 115 |
+
| **`CHO.conditioning`** | 41.7% | **56.9%** | **+15.2%** | Removing irrelevant choices preserves odds ratios (Independence of Irrelevant Alternatives) |
|
| 116 |
+
| **`REP.equivariance`** | 48.6% | **55.6%** | **+7.0%** | Symmetrical probability shifts under negation transformations |
|
| 117 |
+
| **`MEA.partition`** | 30.7% | **41.1%** | **+10.4%** | Probability mass preservation across option clustering |
|
| 118 |
+
| **OVERALL (Strict 0.05)** | **58.67%** | **62.53%** | **+3.86%** | **Official Benchmark Standard** |
|
| 119 |
+
|
| 120 |
+
Machine-readable evaluation reports are archived in `reports/jevbench/`.
|
| 121 |
+
|
| 122 |
+
---
|
| 123 |
+
|
| 124 |
+
## π Quickstart & Usage
|
| 125 |
+
|
| 126 |
+
### 1. Installation
|
| 127 |
+
```bash
|
| 128 |
+
git clone https://github.com/AnkitNayak-dev/QJev-1.5B.git
|
| 129 |
+
cd QJev-1.5B
|
| 130 |
+
pip install -r requirements.txt
|
| 131 |
+
```
|
| 132 |
+
|
| 133 |
+
### 2. Fast Python API (3 Lines of Code)
|
| 134 |
+
```python
|
| 135 |
+
from qjev import QJev
|
| 136 |
+
|
| 137 |
+
# Load ANY edition (Full Standalone, 4-bit Quantized, or LoRA Adapter) in 1 line:
|
| 138 |
+
model = QJev.from_pretrained("devankit7873/QJev-1.5B")
|
| 139 |
+
# Or 4-bit (1.07 GB VRAM): model = QJev.from_pretrained("devankit7873/QJev-1.5B-4bit")
|
| 140 |
+
# Or LoRA (20 MB download): model = QJev.from_pretrained("devankit7873/QJev-1.5B-LoRA")
|
| 141 |
+
|
| 142 |
+
# 1-Line Decision (~31 ms)
|
| 143 |
+
result = model.decide(
|
| 144 |
+
context="Production database primary replica CPU spiked to 100% and connection pool is exhausted.",
|
| 145 |
+
choices=[
|
| 146 |
+
"Trigger immediate automated failover to standby replica",
|
| 147 |
+
"Restart the primary database daemon immediately",
|
| 148 |
+
"Double connection pool limits without scaling compute",
|
| 149 |
+
"Silence alerts and monitor for next 15 minutes"
|
| 150 |
+
]
|
| 151 |
+
)
|
| 152 |
+
|
| 153 |
+
print(f"π Recommended Action: {result['best_choice']} ({result['confidence']}%)")
|
| 154 |
+
for choice, prob in result['probabilities'].items():
|
| 155 |
+
print(f" [{prob:>5.2f}%] {choice}")
|
| 156 |
+
```
|
| 157 |
+
|
| 158 |
+
**Expected Output:**
|
| 159 |
+
```text
|
| 160 |
+
π Recommended Action: Trigger immediate automated failover to standby replica (88.28%)
|
| 161 |
+
[88.28%] Trigger immediate automated failover to standby replica
|
| 162 |
+
[ 6.54%] Restart the primary database daemon immediately
|
| 163 |
+
[ 4.79%] Double connection pool limits without scaling compute
|
| 164 |
+
[ 0.45%] Silence alerts and monitor for next 15 minutes
|
| 165 |
+
```
|
| 166 |
+
|
| 167 |
+
### 3. CLI Command-Line Decision
|
| 168 |
+
```bash
|
| 169 |
+
python qjev.py --context "Patient has severe chest pain and elevated troponin" --choices "Emergency PCI" "Aspirin" "Wait"
|
| 170 |
+
```
|
| 171 |
+
|
| 172 |
+
---
|
| 173 |
+
|
| 174 |
+
## π Multi-Engine Inference Deployment
|
| 175 |
+
|
| 176 |
+
QJev-1.5B natively supports **all standard LLM serving runtimes**:
|
| 177 |
+
|
| 178 |
+
### 1. High-Performance Microservice Server (`serve.py`)
|
| 179 |
+
Run the unified FastAPI server exposing REST, System One, and OpenAI compatible endpoints:
|
| 180 |
+
```bash
|
| 181 |
+
python serve.py --model devankit7873/QJev-1.5B --port 8000
|
| 182 |
+
```
|
| 183 |
+
Endpoints provided:
|
| 184 |
+
* **REST Decision API:** `POST /v1/decide`
|
| 185 |
+
* **Official Jev Protocol (BenchmarkHeaven):** `POST /v1/systemone`
|
| 186 |
+
* **OpenAI Drop-In Compatible:** `POST /v1/chat/completions`
|
| 187 |
+
|
| 188 |
+
Query via cURL:
|
| 189 |
+
```bash
|
| 190 |
+
curl -X POST http://localhost:8000/v1/decide \
|
| 191 |
+
-H "Content-Type: application/json" \
|
| 192 |
+
-d '{
|
| 193 |
+
"context": "Customer requests immediate refund after 45 days.",
|
| 194 |
+
"options": ["Approve refund", "Offer store credit", "Deny request"]
|
| 195 |
+
}'
|
| 196 |
+
```
|
| 197 |
+
|
| 198 |
+
### 2. Ollama (Local Mac / PC / Linux)
|
| 199 |
+
Package and run locally with Ollama using the included `Modelfile`:
|
| 200 |
+
```bash
|
| 201 |
+
ollama create qjev-1.5b -f Modelfile
|
| 202 |
+
ollama run qjev-1.5b
|
| 203 |
+
```
|
| 204 |
+
Or query from Python via `QJev`:
|
| 205 |
+
```python
|
| 206 |
+
from qjev import QJev
|
| 207 |
+
model = QJev.from_ollama("http://localhost:11434", model="qjev-1.5b")
|
| 208 |
+
result = model.decide("Route packet to cluster A or B?", ["Cluster A", "Cluster B"])
|
| 209 |
+
```
|
| 210 |
+
|
| 211 |
+
### 3. llama.cpp / GGUF (LM Studio & Edge CPU)
|
| 212 |
+
Export to GGUF format for edge devices using the export tool:
|
| 213 |
+
```bash
|
| 214 |
+
python scripts/export_gguf.py --model-dir export/QJev-1.5B-Phase3 --out-file qjev-1.5b-f16.gguf
|
| 215 |
+
./llama-quantize qjev-1.5b-f16.gguf qjev-1.5b-q4_k_m.gguf Q4_K_M
|
| 216 |
+
```
|
| 217 |
+
|
| 218 |
+
### 4. vLLM (Production Continuous Batching)
|
| 219 |
+
```bash
|
| 220 |
+
vllm serve devankit7873/QJev-1.5B --task classify --port 8000
|
| 221 |
+
```
|
| 222 |
+
|
| 223 |
+
---
|
| 224 |
+
|
| 225 |
+
## ποΈ Model Architecture
|
| 226 |
+
|
| 227 |
+
```
|
| 228 |
+
[User Context + Formatted Choices]
|
| 229 |
+
β
|
| 230 |
+
βΌ
|
| 231 |
+
ββββββββββββββββββββββββββ
|
| 232 |
+
β Qwen2.5-1.5B Backbone β (QLoRA adapted on q, k, v, o projections)
|
| 233 |
+
βββββββββββββ¬βββββββββββββ
|
| 234 |
+
β (Last Hidden State: 1536 dim)
|
| 235 |
+
βΌ
|
| 236 |
+
ββββββββββββββββββββββββββ
|
| 237 |
+
β LayerNorm(1536) β
|
| 238 |
+
βββββββββββββ¬βββββββββββββ
|
| 239 |
+
β
|
| 240 |
+
βΌ
|
| 241 |
+
ββββββββββββββββββββββββββ
|
| 242 |
+
β Linear(1536 -> 512) β (GELU + Dropout 0.1)
|
| 243 |
+
βββββββββββββ¬βββββββββββββ
|
| 244 |
+
β
|
| 245 |
+
βΌ
|
| 246 |
+
ββββββββββββββββββββββββββ
|
| 247 |
+
β Linear(512 -> 10) β (Dynamic Choice Masking)
|
| 248 |
+
βββββββββββββ¬βββββββββββββ
|
| 249 |
+
β
|
| 250 |
+
βΌ
|
| 251 |
+
[Calibrated Softmax Probabilities]
|
| 252 |
+
```
|
| 253 |
+
|
| 254 |
+
---
|
| 255 |
+
|
| 256 |
+
## π Repository Structure
|
| 257 |
+
|
| 258 |
+
```text
|
| 259 |
+
βββ README.md # Project showcase, benchmarks, and documentation
|
| 260 |
+
βββ LICENSE # Apache 2.0 open-source license
|
| 261 |
+
βββ requirements.txt # Python dependencies
|
| 262 |
+
βββ Modelfile # Ollama build definition
|
| 263 |
+
βββ qjev.py # Universal Python SDK & CLI client
|
| 264 |
+
βββ serve.py # Production FastAPI server (REST, Jev, OpenAI)
|
| 265 |
+
βββ predict.py # Single-pass forward evaluation demo
|
| 266 |
+
βββ handler.py # Hugging Face Inference Endpoint handler
|
| 267 |
+
β
|
| 268 |
+
βββ benchmark/ # JevBench self-test and evaluation suites
|
| 269 |
+
β βββ run_jevbench.py # JevBench metamorphic test harness
|
| 270 |
+
β βββ self_test_benchmarkheaven.py # Official BenchmarkHeaven standard runner
|
| 271 |
+
β βββ self_test_phase3.py # Phase 3 consistency verification runner
|
| 272 |
+
β βββ self_test_step1.py # Calibrated temperature sweep suite
|
| 273 |
+
β
|
| 274 |
+
βββ reports/ # Empirical evaluation records
|
| 275 |
+
β βββ jevbench/ # JSON benchmark results across phases
|
| 276 |
+
β βββ self_test_phase3_consistency.json # Official 62.53% report
|
| 277 |
+
β βββ jevbench_phase1_report.json
|
| 278 |
+
β βββ jevbench_phase2_report.json
|
| 279 |
+
β
|
| 280 |
+
βββ src/ # Core modeling and training code
|
| 281 |
+
β βββ model.py # MLP Decision Head + Qwen architecture
|
| 282 |
+
β βββ dataset.py # Streaming ChatML dataset builder
|
| 283 |
+
β βββ train.py # Phase 1 baseline training
|
| 284 |
+
β βββ train_phase2.py # Phase 2 QLoRA joint training (655k samples)
|
| 285 |
+
β βββ train_phase3_consistency.py # Phase 3 KL consistency alignment
|
| 286 |
+
β βββ evaluate.py # Out-of-Distribution evaluation metrics
|
| 287 |
+
β
|
| 288 |
+
βββ scripts/ # Engineering and deployment utilities
|
| 289 |
+
βββ build_consistency_dataset.py # 20k paired consistency dataset generator
|
| 290 |
+
βββ merge_phase3.py # Phase 3 LoRA fusing & packaging
|
| 291 |
+
βββ merge_and_export.py # Base export utility
|
| 292 |
+
βββ export_gguf.py # GGUF converter for llama.cpp / LM Studio
|
| 293 |
+
βββ publish_all_hf.py # Hugging Face Hub publisher
|
| 294 |
+
βββ download_data.py # Dataset downloader
|
| 295 |
+
βββ download_model.py # Base model downloader
|
| 296 |
+
```
|
| 297 |
+
|
| 298 |
+
---
|
| 299 |
+
|
| 300 |
+
## π» Hardware & Training Infrastructure
|
| 301 |
+
|
| 302 |
+
- **Hardware:** HP OMEN Laptop (NVIDIA GeForce RTX 5060 Laptop GPU, 8GB VRAM)
|
| 303 |
+
- **Host OS:** Windows 11 Pro 64-bit
|
| 304 |
+
- **CUDA / Driver:** CUDA 12.8 / Driver 621.24
|
| 305 |
+
- **Precision:** Float32 Matmul Precision (`high`) with Tensor Core TF32 acceleration
|
| 306 |
+
- **Training Trajectory:**
|
| 307 |
+
- **Phase 1:** MLP Head alignment on frozen backbone (1.5 hrs).
|
| 308 |
+
- **Phase 2:** Joint QLoRA + MLP training across 655,806 samples (18.5 hrs, strictly 5.9 GB VRAM).
|
| 309 |
+
- **Phase 3:** Paired consistency KL alignment (27 mins, 1,250 steps, batch size 16).
|
| 310 |
+
|
| 311 |
+
---
|
| 312 |
+
|
| 313 |
+
## π Citation
|
| 314 |
+
|
| 315 |
+
If you use **QJev-1.5B** or its benchmark methodology, please cite:
|
| 316 |
+
|
| 317 |
+
```bibtex
|
| 318 |
+
@misc{nayak2026qjev15b,
|
| 319 |
+
author = {Ankit Nayak},
|
| 320 |
+
title = {QJev-1.5B: High-Speed System 1 JEV Decision Model based on Qwen2.5},
|
| 321 |
+
year = {2026},
|
| 322 |
+
publisher = {GitHub and Hugging Face},
|
| 323 |
+
howpublished = {\url{https://github.com/AnkitNayak-dev/QJev-1.5B}}
|
| 324 |
+
}
|
| 325 |
+
```
|
| 326 |
+
|
| 327 |
+
---
|
| 328 |
+
|
| 329 |
+
## π License
|
| 330 |
+
This model and codebase are released under the **Apache 2.0 License**.
|
| 331 |
+
Base weights are governed by Alibaba Cloud Qwen License. Distillation corpus is provided by SargeDev (`jev-distill-corpus-v3`).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|