玩模型开放模型 · 清晰来源 · 自主选择
返回模型目录
groxaxo /

Holo4-27B-abliterated-exl3-4bpw

HF 源站

groxaxo/Holo4-27B-abliterated-exl3-4bpw is an uncensored open-source model hosted on Hugging Face.

Image-Text-to-TextsafetensorsLicense: cc-by-nc-4.027Bexllamav3qwen3_5exl3holo4quantizedconversational4-bit
README.md说明 / 使用方法

license: cc-by-nc-4.0 base_model: timteh673/Holo4-27B-Abliterix base_model_relation: quantized library_name: exllamav3 pipeline_tag: image-text-to-text tags:

  • exl3
  • holo4
  • quantized

Holo4-27B-abliterated-exl3-4bpw

Source: timteh673/Holo4-27B-Abliterix at exact revision 5d84c5e11081aa706234a1c90610c86496d01d33. Full-precision BF16 source; source shard SHA-256s verified locally. Abliterated source: True. Source lineage verified against Hcompany/Holo4-27B and the derivative reproducibility manifest.

Non-commercial use only under CC BY-NC 4.0. Attribution: H Company, Holo4-27B; refusal-direction ablation by timteh673 using Abliterix. Original Qwen base Apache-2.0 license also included as LICENSE-APACHE. Changes here: EXL3 quantization and removal of dangling MTP configuration.

Existing EXL3 converter revision 02aef45cd681b960a00afcd0749a4ab99e6c1bfe. Target 4 bpw; converter-reported bitrate 4.0; total tensor-storage bitrate 4.858593 bits per original source parameter, including scales and unquantized tensors. These measures have different denominators. HQ allocation, 8-bit output head, 6-bit vision linear weights, mul1 codebook, output scales always. Calibration: pinned converter bundled mixed corpus, 250 rows × 2048 tokens, deterministic seed 0; six corpus SHA-256s and exact quantization settings are in provenance.json. No measurement reuse.

Native tokenizer and native chat template retained; thinking defaults follow the original template. Validation used native template with thinking disabled. Source config declares MTP, but source tensor index contains no genuine MTP weights: its dangling layer count was set to zero in owned staging. No MTP draft model is included.

The actual exported language model was loaded with EXL3 and generated nonempty text before publication. This is a text smoke validation, not a benchmark of GUI grounding, vision, agent accuracy or refusal behavior. No original benchmark scores are claimed for this quantization. Use EXL3-compatible inference software; this is not an EXL2 or GPTQ checkpoint.

tensor-inventory.json, checksum-manifest.json and provenance.json describe every artifact and the validation. The manifest excludes its own file; its SHA-256 and remote publication commit are recorded in the campaign receipts.

HUGGING FACE

上游数据

HF 下载量0
HF 点赞量0

HF 下载量为源站最近 30 天统计,与本站点击分开。

SITE STATS

本站统计

下载点击—
请求数—
匿名去重—最近 7 天—

本站下载量记录按钮点击,不代表下载完成;短时连点会去重。

来源与版本

作者
groxaxo
最近更新
2026/10/10
最新创建
2026/10/10
HF 趋势
未知
数据快照
2026/10/10
版本
未知
许可证
cc-by-nc-4.0