Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
chopratejas
/
kompress-base
like
1
Token Classification
Transformers
Safetensors
8 datasets
English
modernbert
token-compression
prompt-compression
context-compression
agentic
llmlingua
headroom
tool-outputs
structured-data
Eval Results (legacy)
arxiv:
2403.12968
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
kompress-base
604 MB
1 contributor
History:
5 commits
chopratejas
v4: coherent labels (37K) — Claude-distilled extractive compression, argmax inference
c721d8a
verified
2 days ago
.gitattributes
1.52 kB
initial commit
3 days ago
README.md
5.92 kB
v3: trained on 330K structured tool outputs (H100) — JSON, diffs, logs, code, SQL, agentic traces
3 days ago
config.json
2.78 kB
Initial release: Kompress v1 — ModernBERT token compressor for agentic contexts
3 days ago
model.safetensors
600 MB
xet
v4: coherent labels (37K) — Claude-distilled extractive compression, argmax inference
2 days ago
tokenizer.json
3.58 MB
Initial release: Kompress v1 — ModernBERT token compressor for agentic contexts
3 days ago
tokenizer_config.json
351 Bytes
Initial release: Kompress v1 — ModernBERT token compressor for agentic contexts
3 days ago
training_args.bin
5.2 kB
xet
v4: coherent labels (37K) — Claude-distilled extractive compression, argmax inference
2 days ago
