--- title: Kompress-V2-BASE canonical_url: "https://www.modelscope.cn/models/taally/Kompress-V2-BASE" md_url: "https://www.modelscope.cn/models/taally/Kompress-V2-BASE.md" repository: taally/Kompress-V2-BASE chinese_name: Kompress-V2-BASE last_updated: 2026-08-21 license: apache-2.0 pipeline_tag: text-summarization tasks: - text-summarization model_type: - kompress_v2 architectures: - HeadroomCompressorV2 base_model: - answerdotai/ModernBERT-base base_model_relation: finetune parameters: 153.4M tensor_type: - BF16 - F32 library_name: - pytorch - transformer - lora - safetensors - onnx - tensorflow frameworks: - TensorFlow language: - en downloads: 72 stars: 0 tags: - text-compression - token-classification - modernbert - kompress - LoRA --- # Kompress-V2-BASE > Kompress-V2-BASE - taally 在 ModelScope 开源的模型。Kompress-v2-base is a lightweight token classification model designed for efficient and high-quality context compression in agentic systems. taally/Kompress-V2-BASE 是 ModelScope 魔搭社区上的 153.4M 参数text-summarization模型，采用 apache-2.0 许可，基于 answerdotai/ModernBERT-base 构建。 - **Repository**: taally/Kompress-V2-BASE - **License**: apache-2.0 - **Tasks**: text-summarization - **Parameters**: 153.4M - **Base model**: answerdotai/ModernBERT-base - **Tags**: text-compression, token-classification, modernbert, kompress, LoRA - **Downloads**: 72 - **Stars**: 0 - **Last updated**: 2026-08-21 Source: https://www.modelscope.cn/models/taally/Kompress-V2-BASE --- # kompress-v2-base Extractive prompt compressor for LLM proxies. Predicts a keep/drop label per token; the surviving tokens form a compressed version of the input that preserves meaning while reducing token count. Based on **ModernBERT-base** (149M params) with a LoRA adapter (3.4M trainable params, 2.2%) plus a custom dual head (token classifier + 1-D span conv). Trained on 126,617 accepted Pipeline A+B labels (compressor + faithfulness judge) across 17 domains: narrative, dialog, code, agent traces, healthcare, finance, government, scientific, web, summary, and tool-calling. ## Quick start ```python import torch from transformers import AutoTokenizer # Option A: load the merged checkpoint (no LoRA needed) state = torch.load("merged.pt", map_location="cpu") # Option B: load via the kompress package from kompress.model.architecture import HeadroomCompressorV2 from kompress.model.config import V2_BASE import json with open("config.json") as f: cfg_dict = json.load(f) cfg = V2_BASE # or rebuild from cfg_dict model = HeadroomCompressorV2(cfg) model.load_state_dict(torch.load("merged.pt", map_location="cpu"), strict=False) model.eval().cuda() tokenizer = AutoTokenizer.from_pretrained("chopratejas/kompress-v2-base") # Compress text = "The quick brown fox jumps over the lazy dog." enc = tokenizer(text, return_tensors="pt").to("cuda") with torch.no_grad(): out = model(**enc) scores = out["final_scores"][0] # P(keep) per subword keep = (scores >= 0.5) kept_tokens = enc["input_ids"][0][keep] print(tokenizer.decode(kept_tokens, skip_special_tokens=True)) ``` ## Threshold tuning The model emits `final_scores ∈ [0, 1]` per subword. Adjust the threshold to trade compression aggressiveness for must-keep recall. | Threshold | keep_rate | must_keep_recall | F1 | best for | |---|---|---|---|---| | **0.30** | 0.917 (8% drop) | 0.994 | 0.904 | Conservative | | **0.40** | 0.867 (13% drop) | 0.987 | 0.913 | Safe | | **0.50** (default) | 0.815 (18% drop) | 0.974 | **0.918** | Balanced | | **0.60** | 0.765 (23% drop) | 0.950 | 0.915 | Aggressive | | **0.70** | 0.705 (30% drop) | 0.908 | 0.898 | Very aggressive | Evaluated on the held-out test split (n=7,037 examples, stratified by domain). ## Training data - **126,617 labeled examples** after `min_drop_ratio=0.05` filtering and same-conversation packing. - **Sources**: arxiv, pubmed-scientific, govreport, swe-smith, swe-gym-openhands, toolmind, xlam-fc, fineweb-edu, cnn-dailymail, xsum, glaive-fc, lmsys-chat, claude-code-sessions, meetingbank, the-stack-smol-md, samsum, swe-bench-verified. - **Labeler**: DeepSeek-V4-Flash (compressor) + DeepSeek-V4-Pro (judge) with Pipeline A + B faithfulness loop. Hard-keep overlay enforces names, dates, numbers, URLs, code identifiers via GLiNER + regex + lexicons. - **Bucket split**: short=48%, mid=31%, long=21% (max_length 8,192 native ModernBERT context). - **Split**: train=126,617 / val=7,037 / test=7,037. ## Training details - Base: ModernBERT-base (149M params) - Encoder fine-tuning: **LoRA** (r=16, alpha=32, target_modules=Wqkv/Wi/Wo) - Heads: per-token CE (must-keep loss weight = 3.0) + 1-D span conv (BCE, weight 0.3 on total loss) - Trainable params: 3.4M (2.2% of total) - Loss: weighted cross-entropy on token head + BCE-with-logits on span head - Optim: AdamW (lr=2e-4 cosine, warmup_ratio=0.06, weight_decay=0.01) - Effective batch: 48 (12 × 4 grad-accum) - Epochs: 3 - Precision: bf16 with FlashAttention-2 + gradient checkpointing - Hardware: 1×H100 80GB, ~39 min wall-clock ## Final metrics (test split, threshold=0.5) - eval_f1: 0.918 - eval_must_keep_recall: 0.974 - eval_keep_rate: 0.815 (18% compression) - eval_loss: 0.34 ## Files in this repo ``` config.json # KompressV2Config + arch metadata model.safetensors # ~600 MB — best checkpoint, LoRA merged into the encoder merged.pt # ~600 MB — full state dict, alias for safetensors load tokenizer.json # ModernBERT-base tokenizer tokenizer_config.json special_tokens_map.json adapter/ # LoRA adapter ONLY (~30 MB), for stacking per-org adapters adapter_config.json adapter_model.safetensors token_head.pt span_conv.pt README.md # this file ``` ## License Apache 2.0. Free for commercial use. ModernBERT base is also Apache 2.0. ## See also - [`chopratejas/kompress-v2-large`](https://huggingface.co/chopratejas/kompress-v2-large) — larger variant (ModernBERT-large, 395M params, private/enterprise) - Headroom proxy integration guide: [docs/CUSTOMER_QUICKSTART.md](https://github.com/chopratejas/kompress/blob/main/docs/CUSTOMER_QUICKSTART.md) - Per-org fine-tuning (LoRA stacking): [docs/DEPLOYMENT_STRATEGY.md](https://github.com/chopratejas/kompress/blob/main/docs/DEPLOYMENT_STRATEGY.md)