Hugging Face's logo

interfaze-ai
/
lev

Zero-Shot Classification
PEFT
Safetensors
English
lev
system-one
decision-model
calibrated-decisions
classification
routing
moderation
lora
Model card Files
xet
 Community
1
Abhinav-jigsawstack commited on
Commit
7bdc748
·
verified ·
1 Parent(s): df2865a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -2
README.md CHANGED
@@ -18,8 +18,6 @@ tags:
18
  - lora
19
  ---
20
 
21
- Read full blog here: https://interfaze.ai/blog/jev-now-open-source-lev
22
-
23
  <p align="center">
24
  <img src="assets/hero.png" alt="lev: one state, many typed decisions, one forward pass" width="100%">
25
  </p>
@@ -28,6 +26,10 @@ lev answers typed questions about a piece of context in a single forward pass. Y
28
 
29
  <div align="center" style="line-height: 1;"><img src="https://img.shields.io/badge/license-Apache--2.0-2a78d6?style=flat-square" alt="Apache-2.0" style="display: inline-block; vertical-align: middle; margin: 2px;"> <img src="https://img.shields.io/badge/base-Qwen3.5--4B-2a78d6?style=flat-square" alt="Qwen3.5-4B" style="display: inline-block; vertical-align: middle; margin: 2px;"> <img src="https://img.shields.io/badge/output%20tokens-0-2a78d6?style=flat-square" alt="Zero output tokens" style="display: inline-block; vertical-align: middle; margin: 2px;"> <img src="https://img.shields.io/badge/API-%2Fv1%2Fsystemone-2a78d6?style=flat-square" alt="/v1/systemone compatible" style="display: inline-block; vertical-align: middle; margin: 2px;"> <a href="https://github.com/Abhinavexists/lev"><img src="https://img.shields.io/badge/code-GitHub-14181f?style=flat-square&logo=github" alt="GitHub" style="display: inline-block; vertical-align: middle; margin: 2px;"></a> <a href="https://interfaze.ai/blog/jev-now-open-source-lev"><img src="https://img.shields.io/badge/Blog-lev-yellow" alt="Blog" style="display: inline-block; vertical-align: middle; margin: 2px;"></a> <a href="https://interfaze.ai"><img src="https://img.shields.io/badge/Built_by-Interfaze--ai-4C1" alt="interfaze" style="display: inline-block; vertical-align: middle; margin: 2px;"></a></div>
30
 
 
 
 
 
31
  <h2 align="center">68.9% on all 13 S1Bench subsets. 4B parameters. Zero output tokens.</h2>
32
 
33
  <p align="center"><strong>Qwen3.5-4B + LoRA on one H100.</strong> On the six subsets the public S1Bench board completed, level with reflex-4b and behind only Jev and three open models of 26B–35B.</p>
@@ -139,6 +141,11 @@ Text classification in Interfaze runs on a similar system to lev: the model read
139
  | Questions | Typed only: yes/no, choice, score | Any JSON schema, labels included |
140
  | In the same request | Classification only | OCR, web search, transcription, extraction, and more |
141
  | Where it runs | Your GPU | Interfaze API |
 
 
 
 
 
142
  ```python
143
  import os
144
  from typing import Literal
 
18
  - lora
19
  ---
20
 
 
 
21
  <p align="center">
22
  <img src="assets/hero.png" alt="lev: one state, many typed decisions, one forward pass" width="100%">
23
  </p>
 
26
 
27
  <div align="center" style="line-height: 1;"><img src="https://img.shields.io/badge/license-Apache--2.0-2a78d6?style=flat-square" alt="Apache-2.0" style="display: inline-block; vertical-align: middle; margin: 2px;"> <img src="https://img.shields.io/badge/base-Qwen3.5--4B-2a78d6?style=flat-square" alt="Qwen3.5-4B" style="display: inline-block; vertical-align: middle; margin: 2px;"> <img src="https://img.shields.io/badge/output%20tokens-0-2a78d6?style=flat-square" alt="Zero output tokens" style="display: inline-block; vertical-align: middle; margin: 2px;"> <img src="https://img.shields.io/badge/API-%2Fv1%2Fsystemone-2a78d6?style=flat-square" alt="/v1/systemone compatible" style="display: inline-block; vertical-align: middle; margin: 2px;"> <a href="https://github.com/Abhinavexists/lev"><img src="https://img.shields.io/badge/code-GitHub-14181f?style=flat-square&logo=github" alt="GitHub" style="display: inline-block; vertical-align: middle; margin: 2px;"></a> <a href="https://interfaze.ai/blog/jev-now-open-source-lev"><img src="https://img.shields.io/badge/Blog-lev-yellow" alt="Blog" style="display: inline-block; vertical-align: middle; margin: 2px;"></a> <a href="https://interfaze.ai"><img src="https://img.shields.io/badge/Built_by-Interfaze--ai-4C1" alt="interfaze" style="display: inline-block; vertical-align: middle; margin: 2px;"></a></div>
28
 
29
+ <p align="center">
30
+ Read full blog here: <a href="https://interfaze.ai/blog/jev-now-open-source-lev">https://interfaze.ai/blog/jev-now-open-source-lev</a>
31
+ </p>
32
+
33
  <h2 align="center">68.9% on all 13 S1Bench subsets. 4B parameters. Zero output tokens.</h2>
34
 
35
  <p align="center"><strong>Qwen3.5-4B + LoRA on one H100.</strong> On the six subsets the public S1Bench board completed, level with reflex-4b and behind only Jev and three open models of 26B–35B.</p>
 
141
  | Questions | Typed only: yes/no, choice, score | Any JSON schema, labels included |
142
  | In the same request | Classification only | OCR, web search, transcription, extraction, and more |
143
  | Where it runs | Your GPU | Interfaze API |
144
+
145
+ ```bash
146
+ pip install interfaze
147
+ ```
148
+
149
  ```python
150
  import os
151
  from typing import Literal