Nyansapo Ocr Trocr LoRA v1 0 1
maxtargetlen reduced from 128 → 4 (root fix for hallucination) norepeatngramsize set to 0 (was hurting short outputs) lengthpenalty set to 1.0 (was 2.0 — was pushing model to generate more tokens)
Modellquelle
- Art
- LoRA
- Dateigröße
- 19,2 MB
- Basismodell
- microsoft/trocr-base-handwritten
- Version
- vadapter_model
- Aktualisiert
- 18. Sept. 2026
- Downloads
- 2
- Quelle
- Hugging Face
Quellenbeschreibung
Nyansapo OCR — TrOCR LoRA v1.0.1
What changed from v1.0.0
max_target_lenreduced from 128 → 4 (root fix for hallucination)no_repeat_ngram_sizeset to 0 (was hurting short outputs)length_penaltyset to 1.0 (was 2.0 — was pushing model to generate more tokens)
Training details
- Base model: microsoft/trocr-base-handwritten
- PEFT: LoRA (r=16, alpha=32)
- Dataset: Nzyoka19/ocr_images
Quellen
1 Quelle
Quellen
1 QuelleVerifiziert 3. Sept.
Modellartefakte
1 Artefakt
Modellartefakte
1 Artefaktadapter_model.safetensors
safetensors · 19,2 MB · SHA-256 2acc18493828…b285 · Hugging Face
Download fileQuellenauszüge
2 Auszüge
Quellenauszüge
2 Auszüge--- base_model: microsoft/trocr-base-handwritten tags: [ocr, lora, peft, trocr, image-to-text, nyansapo] license: mit --- # Nyansapo OCR — TrOCR LoRA v1.0.1 ## What changed from v1.0.0 - `max_target_len` reduced from 128 → 4 (root fix for hallucination) - `no_repeat_ngram_size` set to 0 (was hurting short outputs) - `length_penalty` set to 1.0 (was 2.0 — was pushing model to generate more tokens) ## Training details - **Base model:** microsoft/trocr-base-handwritten - **PEFT:** LoRA (r=16, alpha=32) - **Dataset:** Nzyoka19/ocr_images
Source context: 2 downloads · 0 likes · Pipeline image-to-text · Library peft · Repo Nzyoka19/nyansapo-ocr-trocr-lora_v1-0-1
