Instructions to use davidburhans/gevva-e2b-multimodal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use davidburhans/gevva-e2b-multimodal with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="davidburhans/gevva-e2b-multimodal")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSequenceClassification processor = AutoProcessor.from_pretrained("davidburhans/gevva-e2b-multimodal") model = AutoModelForSequenceClassification.from_pretrained("davidburhans/gevva-e2b-multimodal", device_map="auto") - Notebooks
- Google Colab
- Kaggle
β‘ Gevva e2b: The Instant AI Decision Engine
15-millisecond fact checking, hallucination detection, tool routing & chart verification.
100x faster than generative LLMs β’ Runs on laptops & cloud CPUs β’ Global #1 on JevBench
π€ What is Gevva? (The 30-Second Explainer)
When you ask ChatGPT or Claude a question, it generates words one token at a time, like a person typing out an essay. That takes 2 to 5 seconds and burns expensive GPU compute.
That is great for writing a story, but it is painfully slow and expensive for simple decisions:
- "Did the AI make up this answer, or is it actually in the PDF?"
- "Should this customer's message go to billing, shipping, or technical support?"
- "Does the revenue bar chart support this financial claim?"
- "Did the student get the math problem right according to the answer key?"
The Solution: An Instant "Reflex Engine" for AI
Psychologist Daniel Kahneman described human thinking in two modes:
- System 1 (Fast & Intuitive): The brain's instant reflex β recognizing a friend's face or dodging a ball in 15 milliseconds.
- System 2 (Slow & Deliberate): Deliberate reasoning β writing an essay or solving complex math step-by-step.
ββββββββββββββββββββββββββββββββββββββββββ ββββββββββββββββββββββββββββββββββββββββββ
β SYSTEM 1: GEVVA β β SYSTEM 2: CHATGPT / CLAUDE β
β β‘ Makes instant decisions in 15 ms β vs β π’ Generates text token-by-token β
β π° 95% cheaper compute cost β β β³ Takes 2,000 - 5,000 milliseconds β
β π― Confident, calibrated decisions β β πΈ Expensive GPU server bills β
β π Best for: Fact-checks, routing, β β βοΈ Best for: Creative writing, long β
β guardrails, and grading β β essays, and coding from scratch β
ββββββββββββββββββββββββββββββββββββββββββ ββββββββββββββββββββββββββββββββββββββββββ
Gevva is the AI's instant reflex. Instead of typing words slowly, Gevva reads your evidence and outputs a clear, calibrated decision in ~15 milliseconds on a GPU (or ~147 ms on a standard laptop CPU).
π Quickstart in 30 Seconds
pip install gevva
import gevva
# Load model directly from Hugging Face (runs on GPU or standard CPU)
model = gevva.load("davidburhans/gevva-e2b")
# Check if a claim is True, False (Hallucination), or Unproven
document = "The company reported $4.2B in revenue for 2025, a 15% increase over 2024."
claim = "Company revenue exceeded four billion dollars."
probs = model.predict([(document, claim)])
# Output probabilities: [Contradiction, Entailment, Neutral]
# -> [0.01, 0.98, 0.01] ==> 98% Confidence: VERIFIED TRUE!
β‘ What Can Gevva Do for You?
1. π‘οΈ Catch AI Hallucinations in RAG & Documents
Traditional search pipelines waste time asking slow LLMs whether an answer is hallucinated. Gevva checks claims against up to 128,000 tokens of source text in a single forward pass:
retrieved_doc = "Patients taking Medication X showed improved sleep with no reported nausea."
ai_answer = "Medication X causes severe nausea in elderly patients."
probs = model.predict([(retrieved_doc, ai_answer)])[0]
if probs[0] > 0.80:
print("π¨ Alert: AI Hallucination detected! Answer contradicts the source document.")
2. π― Smart Action & Tool Routing (No Prompt Tuning)
When an agent receives a message, what tool should it call next? Gevva evaluates all actions simultaneously:
tools = [
"process_refund: Refund payment to customer bank account",
"track_package: Query live shipping milestones and courier GPS",
"reset_password: Send authentication link to user email",
"search_help_docs: Search FAQs and documentation"
]
user_message = "I ordered this two weeks ago and it still hasn't arrived at my house!"
best_action_idx, scores = model.rerank(user_message, tools)
print("Chosen Action:", tools[best_action_idx]) # -> "track_package" in 15 ms!
3. ποΈ Inspect Financial Charts, Tables & Images
Need to check if a claim matches a real chart or invoice? Gevva's multimodal engine inspects images directly:
from PIL import Image
vision_engine = gevva.load("davidburhans/gevva-e2b-multimodal")
chart = Image.open("quarterly_sales.png")
result = vision_engine.predict(
pairs=[("A financial bar chart is shown.", "Q3 sales were higher than Q4.")],
images=[chart]
)
print("Verdict:", result)
4. π Instant Homework & AI Grader
Grade an answer against a reference answer key without human grading fatigue:
grade = model.grade(
question="What is the capital of Australia?",
reference="Canberra",
candidate="The capital city of Australia is Canberra."
)
print(f"Passed: {grade.is_correct} (Confidence: {grade.score*100:.1f}%)")
# -> Passed: True (Confidence: 96.4%)
π» Runs Everywhere (No GPU Required!)
You don't need an expensive datacenter GPU. Gevva was engineered to run blisteringly fast on standard CPUs:
- Runs on Ordinary Laptops: Low memory footprint (~4.8 GB RAM).
- Fast Startup: Loads in 1.2 seconds.
- CPU Speed: Makes decisions in ~147 ms on a CPU β faster than GPT-4 can generate its very first word!
| Hardware | Latency per Decision | What You Can Run |
|---|---|---|
| NVIDIA GPU (RTX 5090) | 14β16 ms | High-throughput enterprise API clusters |
| Standard Cloud CPU / MacBook | 147 ms | Local agents, serverless functions, low-cost microservices |
π Leaderboard & Accuracy
On the official JevBench benchmark evaluating System 1 decision-making across hundreds of real-world scenarios:
| Rank | Model | Parameters | Decision Latency | Composite Score | Open Source? |
|---|---|---|---|---|---|
| π₯ #1 | Gevva e2b (Ours) |
2.3B | 14.3 ms | 77.54 |
Yes (Apache 2.0) |
| π₯ #2 | OpenJEV (AlexWortega) | 2.6B | 18.2 ms | 76.01 |
Yes |
| π₯ #3 | TypeSafe AI Jev | 2.5B | 15.0 ms | 75.40 |
No (Closed API) |
| #4 | Convai Laya | 2.2B | 18.4 ms | 73.80 |
Proprietary |
| #5 | ModernCE Large NLI | 1.8B | 16.1 ms | 72.10 |
Yes |
π¦ Model Variants
| Variant | Repository | Best For |
|---|---|---|
| Flagship (Text Reasoning) | davidburhans/gevva-e2b |
Pure text: RAG hallucination checks, tool routing, document verification. |
| Multimodal (Vision Grounding) | davidburhans/gevva-e2b-multimodal |
Text + Vision: Charts, tables, receipts, invoices, and photos. |
π₯ Authors & Co-Authorship
- Dave Burhans β Lead Author & Architecture
- Gemini 3.8 Flash β Co-Author (Synthetic curriculum generation, 4-judge validator committee, SDK implementation)
- GLM 5.3 β Co-Author (Reasoning remediation curriculum, error audits, adversarial methodology review)
- GLM 5.3 Flash β Co-Author (Synthetic calibration testing, loss formulation, decision metrics)
- Gevva Contributors
π License & Terms
Gevva e2b is released under the Apache 2.0 License. Underlying foundation weights inherit Google's Gemma Terms of Use.
@software{gevva2026,
author = {Burhans, Dave and {Gemini 3.8 Flash} and {GLM 5.3} and {GLM 5.3 Flash} and Contributors},
title = {Gevva: State-of-the-Art Multimodal 128K System 1 Decision Engine},
year = {2026},
publisher = {Hugging Face / GitHub},
url = {https://github.com/davidburhans/gevva}
}
- Downloads last month
- 24
Model tree for davidburhans/gevva-e2b-multimodal
Space using davidburhans/gevva-e2b-multimodal 1
Evaluation results
- JevBench Composite Scoreself-reported77.540
- JevBench Intelligence Scoreself-reported73.910
- JevBench Calibration Scoreself-reported86.900
- Forward Latency (P50)self-reported16.500