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 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
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 works unchanged:
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.
tac-1 is a derivative work of 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.