Qwopus3.6 27B v2 Heretic
This is a full merged safetensors export produced with p-e-w/heretic.
Modellquelle
- Art
- Text model
- Dateigröße
- Noch nicht aufgezeichnet
- Basismodell
- Jackrong/Qwopus3.6-27B-v2
- Version
- vRevision e264f3d
- Aktualisiert
- 3. Okt. 2026
- Verleger
- @kang926
- Downloads
- 18
- Parameter
- 27B
- Quelle
- Hugging Face
Quellenbeschreibung
Qwopus3.6-27B-v2 Heretic
Base model: Jackrong/Qwopus3.6-27B-v2
This is a full merged safetensors export produced with p-e-w/heretic.
Build
- Heretic version:
1.3.0 - Quantization during Heretic:
none - Selected trial:
64 - Export type: full merged safetensors
- Refusals:
5/100 - KL divergence:
0.0070
Notes
The model was smoke-tested with Transformers using enable_thinking=False.
Manual checks covered Korean instruction following, long-answer repetition,
unnecessary clarification behavior, JSON-format following, long-context recall,
and repeated sampling consistency.
Quellen
1 Quelle
Quellen
1 QuelleVerifiziert 3. Okt.
Quellenauszüge
3 Auszüge
Quellenauszüge
3 Auszüge--- base_model: Jackrong/Qwopus3.6-27B-v2 library_name: transformers tags: - heretic - qwen3.6 - safetensors --- # Qwopus3.6-27B-v2 Heretic Base model: `Jackrong/Qwopus3.6-27B-v2` This is a full merged safetensors export produced with `p-e-w/heretic`. ## Build - Heretic version: `1.3.0` - Quantization during Heretic: `none` - Selected trial: `64` - Export type: full merged safetensors - Refusals: `5/100` - KL divergence: `0.0070` ## Notes The model was smoke-tested with Transformers using `enable_thinking=False`. Manual checks covered Korean instruction following, long-answer repetition, unnecessary clarification behavior, JSON-format following, long-context recall, and repeated sampling consistency.
Source context: 18 downloads · 3 likes · Pipeline image-text-to-text · Library transformers · Repo kang926/Qwopus3.6-27B-v2-heretic
Source context: 22 downloads · 4 likes · Pipeline image-text-to-text · Library transformers · Repo kang926/Qwopus3.6-27B-v2-heretic
