Paritok-official / paritok-4b-v1

What it does

• Code-native. Trained on real coding-agent trajectories (file_read, bash_command, log_output, …). It knows what an import statement is worth vs a debug line, so it protects function names, paths, and error strings while compressing.
• Extractive. audited, not asserted. It selects spans instead of rewriting them: 96.2% of the identifiers, paths, and numbers it emits on held-out SWE-bench Lite are copied straight from the input, so an exact-match edit against compressed c
• Compresses each segment to 25.7% of original. 2× harder than gpt-4.1-mini (50.2% CR) and 2.4× harder than gpt-5 (61.9% CR).
• Retains 86.5% of full-context solve quality on SWE-bench Lite (89.3% fed the line-numbered input it was trained for, where the paired difference against uncompressed is not significant, p = 0.079) — matching gpt-4.1-mini as compressor at le
• Small & self-hostable. 4B LoRA adapter, bf16, runs on a single 24GB GPU. No SaaS, no lock-in, no per-token compressor fee.