| --- |
| license: apache-2.0 |
| language: |
| - es |
| base_model: CodeStrux-Tech/tac-1 |
| base_model_relation: quantized |
| pipeline_tag: text-generation |
| tags: |
| - fp8 |
| - compressed-tensors |
| - llmcompressor |
| - address-parsing |
| - costa-rica |
| - qwen3 |
| --- |
| |
| # tac-1-fp8-dynamic — FP8 dynamic quantization of tac-1 |
|
|
| ## Overview |
|
|
| tac-1-fp8-dynamic is quantized from [`CodeStrux-Tech/tac-1`](https://huggingface.co/CodeStrux-Tech/tac-1) using llmcompressor 0.12.0 with the FP8_DYNAMIC scheme. Targets are `Linear` layers; `lm_head` is ignored. The result is a single 4.2 GB shard. |
|
|
| sha256: `e0eb5c3c62e8a472eaca6f86064efb2597863f0688ac3ca1fd9a325390d9c30f` |
|
|
| ## Serving |
|
|
| ```bash |
| vllm serve CodeStrux-Tech/tac-1-fp8-dynamic --served-model-name tac-1 --max-model-len 4096 |
| # On hosts without nvcc, disable the FlashInfer sampler JIT: |
| # VLLM_USE_FLASHINFER_SAMPLER=0 vllm serve ... |
| ``` |
|
|
| No `--quantization` flag is needed — vLLM auto-detects the FP8 format from the model config. The FP8 model is a drop-in replacement for the bf16 original; the client snippet from [`CodeStrux-Tech/tac-1`](https://huggingface.co/CodeStrux-Tech/tac-1) works unchanged: |
|
|
| ```python |
| from tico.extractor.clients.vllm import VLLMExtractor |
| |
| extractor = VLLMExtractor() # VLLM_BASE_URL=http://localhost:8000/v1, TICO_VLLM_MODEL=tac-1 |
| addr = extractor.extract("del antiguo higuerón de San Pedro, 100 metros sur") |
| print(addr.model_dump_json(indent=2)) |
| ``` |
|
|
| ## Evaluation |
|
|
| | metric | tac-1 (bf16) | tac-1 (FP8) | teacher gpt-4.1 | |
| |---|---|---|---| |
| | parse rate | 1.000 | 1.000 | 1.000 | |
| | anchor_name F1 | 0.979 | 0.979 | 0.872 | |
| | direction F1 | 0.995 | 0.984 | 1.000 | |
| | distance F1 | 0.995 | 0.984 | 1.000 | |
| | perfect-anchor ≤250 m | 93.6% | 93.6% | 93.6% | |
| | perfect-anchor median | 0.0 m | 0.0 m | 0.0 m | |
| | gazetteer ≤250 m | 80.9% | 80.9% | 83.0% | |
| |
| ## Training data attribution |
| |
| Contains information from OpenStreetMap (https://www.openstreetmap.org/copyright), which is made available under the Open Database License (ODbL) 1.0. © OpenStreetMap contributors. |
| |
| For full training details, architecture, evaluation, and limitations, see [`CodeStrux-Tech/tac-1`](https://huggingface.co/CodeStrux-Tech/tac-1). |
| |
| tac-1 is a derivative work of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507), Copyright 2024 Alibaba Cloud, licensed under the Apache License, Version 2.0. The upstream LICENSE is included in this repository. |
| |
