Downloads · 30 days
0
Saarthi
Himvans/Saarthi
Saarthi is a text classification model from Himvans. Use it when you need a label for a piece of text. It is set up for laya. The card lists the license as apache-2.0.
Saarthi (Hindi for charioteer — steers and guides toward the goal) fine-tunes convaiinnovations/laya to pick the next browser operation (click / typetext / select) and target element in one non-autoregressive forward…
Access
Public
Updated Sep 26, 2026
Parameters
322M
7.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 97%
At a glance
- Task
- Text Classification
- Library
- laya
- License
- apache-2.0
- Access
- Public
- Created
- Sep 23, 2026
- Updated
- Sep 26, 2026
- SHA
- a9402275
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
Saarthi (सारथी) — laya fine-tuned for browser use
Saarthi (Hindi for charioteer — steers and guides toward the goal) fine-tunes convaiinnovations/laya to pick the next browser operation (click / type_text / select) and target element in one non-autoregressive forward pass. Open replacement for the proprietary decision model in browser-use/jev-ultrafast.
Training data
osunlp/Mind2Web — real action traces across 137 sites. Each step -> operation-choice + target-choice (pos + sampled negatives).
Usage
import laya
agent = laya.load("Himvans/Saarthi")
agent.predict(state, questions) # state has task+elements; questions are typed choices
type_text values need a small LLM (laya is a classifier), same as jev-ultrafast.
License
Apache-2.0 (inherits base).
- Task
- Text Classification
- Library
- laya
- License
- apache-2.0
- Created
- Sep 23, 2026
- Updated
- Sep 26, 2026