VFAi-X legacy vision-language lineage
Historical Qwen3.5-derived vision-language research weights for chart and market-context experiments. The published configuration uses Qwen3_5ForConditionalGeneration (qwen3_5). This family uses third-party foundation weights and is distinct from Qovaryx's random-initialized scratch bases.
Status — October 3, 2026: Qovaryx is on the back burner. Desktop downloads are paused; there is no current public installer, purchase, or trial. These repositories remain as research references. Published weights are separate from desktop product availability.
Artifact and lineage
The repository contains a full sharded Safetensors checkpoint, configuration, tokenizer, and processor assets. The upstream family is Qwen3.5-9B. The earlier card used the noncanonical identifier Qwen3.5-9B-VL; the base-model reference has been corrected.
The repository also retains historical v3.7 and vfai-x-sniper-options branches. They are separate snapshots; inspect their files and revision before use. A legacy branch is not a currently supported desktop release or a claim of superior trading outcomes.
Historical evidence
Earlier cards combined branch-specific abstention and matched-output results with active installer and runtime claims. These have been removed. A result for one historical prompt set or branch cannot establish future profitability, general chart understanding, or the readiness of the current application.
Research loading
Use a Transformers release that supports the architecture in this checkpoint's configuration, together with the supplied processor and tokenizer. Follow the upstream Qwen documentation for compatible multimodal inputs, then verify compatibility with this particular checkpoint and revision. Loading or inference was not rerun during this documentation update.
The earlier vLLM instructions described a legacy serving path; they are not a description of Qovaryx's current integration. GPU-memory and quantization requirements depend on the runtime and workload and are not certified by this card.
Model output can be incorrect or unsupported by the input. Labels such as BUY, SELL, HOLD, or NO_TRADE are experimental output conventions, not authorization to trade or a validated investment recommendation.
License and attribution
Apache-2.0, as recorded in the existing model metadata and repository license. Retain applicable Qwen and other third-party notices. Attribution to the foundation model is required to describe this lineage accurately.
Project and support
J.E. Herizon LLC, doing business as JE Horizon.