Text Classification
Transformers
Safetensors
English
Chinese
qwen3_5_moe_text
text-generation
decision-model
web-agent
browser-agent
typed-decisions
structured-output
one-pass
mixture-of-experts
Instructions to use Lexmount/WebJev-35B-A3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Lexmount/WebJev-35B-A3B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Lexmount/WebJev-35B-A3B")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Lexmount/WebJev-35B-A3B") model = AutoModelForCausalLM.from_pretrained("Lexmount/WebJev-35B-A3B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
23 days ago
-
Document community GGUF conversions and llama.cpp adapter
Verified signature679020a
-
Release the model under Apache-2.0
Verified signatureThe weights can be downloaded, used, fine-tuned and redistributed, including commercially. LICENSE now holds the Apache License 2.0 text, so the duplicate LICENSE-APACHE is removed.cf6824c -
Model card: evaluation link, simplified live-web figure and table
Verified signature844d4f7 -
Model card: introduce the model first, new live-web figure, drop the benchmark chart
Verified signature8896002 -
Model card: lead with the model's value and the live-web results
Verified signature069af2b -
Model card: eight benchmarks, links to code, dataset and training recipe
Verified signaturecab63ef -
Model card: link the WebJev dataset
Verified signature89b287f -
Model card: figures and evaluation
Verified signaturee75083f -
Add model card and license
Verified signature8ed0666