41 lines
1.6 KiB
Markdown
41 lines
1.6 KiB
Markdown
---
|
|
base_model: Qwen/Qwen2.5-7B-Instruct
|
|
base_model_relation: finetune
|
|
library_name: transformers
|
|
license: apache-2.0
|
|
language:
|
|
- en
|
|
pipeline_tag: text-generation
|
|
tags:
|
|
- legacy
|
|
- unsupported
|
|
- not-for-production
|
|
- h-res
|
|
- tool-calling
|
|
---
|
|
|
|
# Legacy / unsupported — H-Res runtime claims withdrawn
|
|
|
|
**Status as of 2026-07-27:** this repository is retained for provenance. It is not an active Uraion
|
|
Labs product, is not used by FinStruct, and should not be deployed as an H-Res model.
|
|
|
|
The audit found 84 `model.layers.*.hres.*` tensors in `model.safetensors`, but `config.json` declares
|
|
the stock `Qwen2ForCausalLM` architecture and contains no `auto_map`, custom model class, or loader
|
|
that instantiates H-Res modules. The repository also contains no custom modeling code. Standard
|
|
Transformers and vLLM loading therefore has no runtime module that consumes those tensors. Prior
|
|
claims that H-Res loads automatically or has full vLLM support are withdrawn.
|
|
|
|
Additional gaps:
|
|
|
|
- no held-out tool-use scores, raw predictions, base-model comparison, or reproducible evaluation;
|
|
- training loss is not evidence of downstream capability;
|
|
- the separate GGUF repository explicitly omits the H-Res tensors and is not a faithful H-Res
|
|
deployment.
|
|
|
|
The full pre-audit card is preserved in [`LEGACY_CARD.md`](LEGACY_CARD.md). The files remain public
|
|
for inspection, not as a supported model release.
|
|
|
|
Current Uraion Labs work is [FinStruct](https://github.com/arnavprabhu/uraion-finstruct): auditable,
|
|
local-first SEC filing extraction with evidence-linked benchmarks. See
|
|
[uraionlabs.com](https://uraionlabs.com).
|