chopratejas
/

kompress-base

Token Classification

token-compression

context-optimization

Eval Results (legacy)

Model card Files Files and versions

760 MB

Ctrl+K

Ctrl+K

1 contributor

History: 10 commits

chopratejas's picture

Add ONNX INT8 model (156MB, no torch dependency needed)

1c91234 verified about 1 month ago

onnx
Add ONNX INT8 model (156MB, no torch dependency needed) about 1 month ago
.gitattributes

1.52 kB
initial commit 2 months ago
README.md

6.42 kB
Update: v9 results (7.9/10 quality), add kompress-small comparison about 2 months ago
config.json

2.78 kB
Initial release: Kompress v1 — ModernBERT token compressor for agentic contexts 2 months ago
model.safetensors

600 MB
xet

Update to v8: density-aware compression (293K Sonnet 4.6 labels with density tags) about 1 month ago
tokenizer.json

3.58 MB
Initial release: Kompress v1 — ModernBERT token compressor for agentic contexts 2 months ago
tokenizer_config.json

351 Bytes
Initial release: Kompress v1 — ModernBERT token compressor for agentic contexts 2 months ago
training_args.bin
Detected Pickle imports (10)
- "accelerate.state.PartialState",
- "transformers.training_args.TrainingArguments",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "torch.device",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.HubStrategy",
- "transformers.training_args.OptimizerNames"
How to fix it?
5.2 kB
xet

Update to v8: density-aware compression (293K Sonnet 4.6 labels with density tags) about 1 month ago