Image-Text-to-Text
GGUF
German
English
ocr
vision
german
invoice-extraction
llama-cpp
ollama
conversational
Instructions to use Keyven/german-ocr-3.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Keyven/german-ocr-3.1 with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf Keyven/german-ocr-3.1:Q4_K_M # Run inference directly in the terminal: llama cli -hf Keyven/german-ocr-3.1:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Keyven/german-ocr-3.1:Q4_K_M # Run inference directly in the terminal: llama cli -hf Keyven/german-ocr-3.1:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf Keyven/german-ocr-3.1:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Keyven/german-ocr-3.1:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf Keyven/german-ocr-3.1:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Keyven/german-ocr-3.1:Q4_K_M
Use Docker
docker model run hf.co/Keyven/german-ocr-3.1:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use Keyven/german-ocr-3.1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Keyven/german-ocr-3.1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Keyven/german-ocr-3.1", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/Keyven/german-ocr-3.1:Q4_K_M
- Ollama
How to use Keyven/german-ocr-3.1 with Ollama:
ollama run hf.co/Keyven/german-ocr-3.1:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use Keyven/german-ocr-3.1 with Docker Model Runner:
docker model run hf.co/Keyven/german-ocr-3.1:Q4_K_M
- Lemonade
How to use Keyven/german-ocr-3.1 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Keyven/german-ocr-3.1:Q4_K_M
Run and chat with the model
lemonade run user.german-ocr-3.1-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Commit ·
86a86b5
0
Parent(s):
Release
Browse files- .gitattributes +39 -0
- README.md +172 -0
- chat_template.jinja +16 -0
- german-ocr-3.1-F16.gguf +3 -0
- german-ocr-3.1-Q4_K_M.gguf +3 -0
- german-ocr-3.1-Q8_0.gguf +3 -0
- mmproj-german-ocr-3.1-F16.gguf +3 -0
.gitattributes
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
german-ocr-3.1-F16.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
german-ocr-3.1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
german-ocr-3.1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
mmproj-german-ocr-3.1-F16.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,172 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- de
|
| 5 |
+
- en
|
| 6 |
+
tags:
|
| 7 |
+
- ocr
|
| 8 |
+
- vision
|
| 9 |
+
- german
|
| 10 |
+
- invoice-extraction
|
| 11 |
+
- gguf
|
| 12 |
+
- llama-cpp
|
| 13 |
+
- ollama
|
| 14 |
+
pipeline_tag: image-text-to-text
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# 👁 German-OCR-3.1
|
| 18 |
+
|
| 19 |
+
> **Das deutsche Vision-OCR-Modell von [Keyvan.ai](https://german-ocr.de) — Teil der German-OCR-3 Kollektion.**
|
| 20 |
+
|
| 21 |
+
```bash
|
| 22 |
+
ollama run Keyvan/german-ocr-3.1
|
| 23 |
+
```
|
| 24 |
+
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
## Die Geschichte
|
| 28 |
+
|
| 29 |
+
German-OCR-3 begann als kleine Idee: ein Modell, das **deutsche Geschäftsdokumente**
|
| 30 |
+
wirklich versteht — Rechnungen, Briefe, Bescheide, Quittungen, Verträge.
|
| 31 |
+
Nicht „auch deutsch", sondern auf deutsche Bürokratie und deutsches Layout spezialisiert.
|
| 32 |
+
|
| 33 |
+
Die **3.1-Generation** ist die feinabgestimmte, engineered + optimierte Version dieser
|
| 34 |
+
Kollektion. Zwei spezialisierte Modelle:
|
| 35 |
+
|
| 36 |
+
| Modell | Rolle |
|
| 37 |
+
|---|---|
|
| 38 |
+
| **👁 German-OCR-3.1** *(du bist hier)* | Vision-OCR — Bild rein, sauberes JSON raus |
|
| 39 |
+
| 🇩🇪 [**German-Text-3.1**](https://ollama.com/Keyvan/german-text-3.1) | Text-Assistent für Übersetzung, Zusammenfassung, Analyse, Chat |
|
| 40 |
+
|
| 41 |
+
OCR-3.1 wurde mit harten Regeln für **Halluzinations-Vermeidung** konfiguriert:
|
| 42 |
+
lieber `null` als geraten, Originalschreibweise behalten, sender vs. recipient
|
| 43 |
+
sauber trennen — das alles ist Pflicht in der Engineering-Konfiguration.
|
| 44 |
+
|
| 45 |
+
---
|
| 46 |
+
|
| 47 |
+
## ✨ Was kann das Modell?
|
| 48 |
+
|
| 49 |
+
**Bild rein → Strukturiertes JSON raus.**
|
| 50 |
+
|
| 51 |
+
| Doc-Typ | Erkennt |
|
| 52 |
+
|---|---|
|
| 53 |
+
| 🧾 **Rechnung** | sender, recipient, IBAN, USt-ID, line_items, amount_net/vat/total, due_date, payment_terms |
|
| 54 |
+
| 📬 **Brief** | sender, recipient, Betreff, Datum, Aktenzeichen |
|
| 55 |
+
| 📋 **Formular** | Felder, Werte, Unterschriften-Felder |
|
| 56 |
+
| 🧾 **Quittung** | Händler, Datum, Positionen, Summe, Steuersatz |
|
| 57 |
+
| ⚖️ **Bescheid** | Behörde, Aktenzeichen, Empfänger, Betrag, Frist |
|
| 58 |
+
| 📄 **Vertrag** | Parteien, Datum, Schlüsselklauseln |
|
| 59 |
+
|
| 60 |
+
### JSON Output Schema
|
| 61 |
+
|
| 62 |
+
```json
|
| 63 |
+
{
|
| 64 |
+
"document_type": "invoice",
|
| 65 |
+
"language": "de",
|
| 66 |
+
"invoice_number": "...",
|
| 67 |
+
"invoice_date": "YYYY-MM-DD",
|
| 68 |
+
"due_date": "YYYY-MM-DD",
|
| 69 |
+
"sender": {"name": "...", "address": "...", "vat_id": "...", "iban": "..."},
|
| 70 |
+
"recipient": {"name": "...", "address": "...", "customer_id": "..."},
|
| 71 |
+
"line_items": [
|
| 72 |
+
{"position": 1, "description": "...", "quantity": 1, "unit": "Stueck",
|
| 73 |
+
"unit_price_net": 0.00, "amount_net": 0.00, "vat_rate": 19}
|
| 74 |
+
],
|
| 75 |
+
"amount_net": 0.00, "amount_vat": 0.00, "amount_total": 0.00,
|
| 76 |
+
"currency": "EUR",
|
| 77 |
+
"notes": []
|
| 78 |
+
}
|
| 79 |
+
```
|
| 80 |
+
|
| 81 |
+
**Garantien:**
|
| 82 |
+
- ✅ JSON-Validität
|
| 83 |
+
- ✅ `null` statt erfundener Werte (Halluzinations-Stop-Regel)
|
| 84 |
+
- ✅ Originalschreibweise + Umlaute
|
| 85 |
+
- ✅ ISO-Datum, Punkt-Dezimal, EUR-Code
|
| 86 |
+
- ✅ sender ≠ recipient klar getrennt
|
| 87 |
+
|
| 88 |
+
---
|
| 89 |
+
|
| 90 |
+
## 🚀 Quick Start
|
| 91 |
+
|
| 92 |
+
### Ollama (1 Zeile)
|
| 93 |
+
|
| 94 |
+
```bash
|
| 95 |
+
ollama run Keyvan/german-ocr-3.1
|
| 96 |
+
```
|
| 97 |
+
|
| 98 |
+
API mit Bild:
|
| 99 |
+
|
| 100 |
+
```bash
|
| 101 |
+
curl http://localhost:11434/api/chat -d '{
|
| 102 |
+
"model": "Keyvan/german-ocr-3.1",
|
| 103 |
+
"messages": [{
|
| 104 |
+
"role": "user",
|
| 105 |
+
"content": "Extrahiere als JSON.",
|
| 106 |
+
"images": ["BASE64_IMAGE_HERE"]
|
| 107 |
+
}],
|
| 108 |
+
"think": false
|
| 109 |
+
}'
|
| 110 |
+
```
|
| 111 |
+
|
| 112 |
+
### llama-server (HF GGUF, Two-File-Pattern)
|
| 113 |
+
|
| 114 |
+
```bash
|
| 115 |
+
hf download Keyven/german-ocr-3.1 \
|
| 116 |
+
german-ocr-3.1-Q8_0.gguf \
|
| 117 |
+
mmproj-german-ocr-3.1-F16.gguf
|
| 118 |
+
|
| 119 |
+
llama-server \
|
| 120 |
+
-m german-ocr-3.1-Q8_0.gguf \
|
| 121 |
+
--mmproj mmproj-german-ocr-3.1-F16.gguf \
|
| 122 |
+
--port 8080 -ngl 99
|
| 123 |
+
```
|
| 124 |
+
|
| 125 |
+
---
|
| 126 |
+
|
| 127 |
+
## 📦 Files (auf [HuggingFace](https://huggingface.co/Keyven/german-ocr-3.1))
|
| 128 |
+
|
| 129 |
+
| File | Größe | Use case |
|
| 130 |
+
|---|---|---|
|
| 131 |
+
| `german-ocr-3.1-Q4_K_M.gguf` | 941 MB | Compact / Edge |
|
| 132 |
+
| `german-ocr-3.1-Q8_0.gguf` | 1.6 GB | ⭐ **Recommended** |
|
| 133 |
+
| `german-ocr-3.1-F16.gguf` | 2.9 GB | Full precision |
|
| 134 |
+
| `mmproj-german-ocr-3.1-F16.gguf` | 1.3 GB | **Required** für Vision (llama-server) |
|
| 135 |
+
|
| 136 |
+
> **Hinweis**: Über Ollama Hub bekommst du das Modell als single-package mit Vision —
|
| 137 |
+
> der mmproj-Sidecar wird nur für die manuelle llama-server-Route benötigt.
|
| 138 |
+
|
| 139 |
+
---
|
| 140 |
+
|
| 141 |
+
## 🛠 Hardware
|
| 142 |
+
|
| 143 |
+
| Variant | RAM (CPU) | VRAM (GPU) |
|
| 144 |
+
|---|---|---|
|
| 145 |
+
| Q4 + Vision | 4 GB | 4 GB |
|
| 146 |
+
| Q8 + Vision | 6 GB | 6 GB |
|
| 147 |
+
| F16 + Vision | 10 GB | 10 GB |
|
| 148 |
+
|
| 149 |
+
GPU empfohlen für Echtzeit-OCR. Context: **32 768 Tokens**.
|
| 150 |
+
|
| 151 |
+
---
|
| 152 |
+
|
| 153 |
+
## 🤝 German-OCR Familie
|
| 154 |
+
|
| 155 |
+
| | Was | Wo |
|
| 156 |
+
|---|---|---|
|
| 157 |
+
| 👁 **German-OCR-3.1** | Vision-OCR (du bist hier) | [ollama.com](https://ollama.com/Keyvan/german-ocr-3.1) · [HF](https://huggingface.co/Keyven/german-ocr-3.1) |
|
| 158 |
+
| 🇩🇪 **German-Text-3.1** | Text-Assistent | [ollama.com](https://ollama.com/Keyvan/german-text-3.1) · [HF](https://huggingface.co/Keyven/german-text-3.1) |
|
| 159 |
+
| ☁️ **German-OCR Cloud API** | Managed Service mit höherer Genauigkeit | [german-ocr.de](https://german-ocr.de) |
|
| 160 |
+
| 📝 **German-OCR for Word** | Office Add-in | [office.german-ocr.de](https://office.german-ocr.de) |
|
| 161 |
+
|
| 162 |
+
---
|
| 163 |
+
|
| 164 |
+
## 📜 License & Credits
|
| 165 |
+
|
| 166 |
+
**Apache License 2.0** — kommerzielle Nutzung mit Attribution erlaubt.
|
| 167 |
+
|
| 168 |
+
**NOTICE**: Aufgebaut auf [Qwen3.5](https://qwenlm.github.io/) von Alibaba Cloud.
|
| 169 |
+
Die German-OCR-3.1-Kollektion ist eine in Deutschland engineered + optimierte
|
| 170 |
+
Distribution für deutsche Geschäftsdokumente. Architecture credit: Qwen Team.
|
| 171 |
+
|
| 172 |
+
Build mit ❤️ in 🇩🇪 von **[Keyvan Hardani](https://german-ocr.de)**.
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set DEFAULT_SYSTEM = "Du bist German-OCR-3.1, das deutsche Vision- und OCR-Modell von Keyvan.ai. Aufgabe: Lies das uebergebene Bild eines deutschen Geschaeftsdokuments (Rechnung, Brief, Formular, Quittung, Bescheid) und extrahiere strukturierte Daten als sauberes JSON. Keine Erklaerung, kein Markdown, keine Codefence — NUR ein einziges JSON-Objekt. WENN ein Wert nicht im Bild steht, gib null. Bevorzuge null vor halluzinierten Werten. Originalschreibweise und Umlaute beibehalten. Datumsangaben YYYY-MM-DD wenn eindeutig. Geldbetraege als Dezimal mit Punkt. Waehrung als ISO-Code (EUR). Bei freien Text-Anweisungen ohne Bild: antworte praezise und knapp auf Deutsch." -%}
|
| 2 |
+
{%- if messages and messages[0]['role'] == 'system' -%}
|
| 3 |
+
<|im_start|>system
|
| 4 |
+
{% if messages[0]['content'] is string %}{{ messages[0]['content'] }}{% else %}{% for c in messages[0]['content'] %}{% if c.type == 'text' %}{{ c.text }}{% endif %}{% endfor %}{% endif %}<|im_end|>
|
| 5 |
+
{% set messages = messages[1:] %}
|
| 6 |
+
{%- else -%}
|
| 7 |
+
<|im_start|>system
|
| 8 |
+
{{ DEFAULT_SYSTEM }}<|im_end|>
|
| 9 |
+
{%- endif -%}
|
| 10 |
+
{%- for message in messages -%}
|
| 11 |
+
<|im_start|>{{ message['role'] }}
|
| 12 |
+
{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for c in message['content'] %}{% if c.type == 'text' %}{{ c.text }}{% elif c.type == 'image' %}<|vision_start|><|image_pad|><|vision_end|>{% endif %}{% endfor %}{% endif %}<|im_end|>
|
| 13 |
+
{% endfor -%}
|
| 14 |
+
{%- if add_generation_prompt -%}
|
| 15 |
+
<|im_start|>assistant
|
| 16 |
+
{% endif -%}
|
german-ocr-3.1-F16.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff8c0b83a98de59fa85743a8a2ece77262afee225e729785344fa1547285d435
|
| 3 |
+
size 3093668736
|
german-ocr-3.1-Q4_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3f83394db914c14e5893e84dbe368b4e4b71c5a6c0489169ed694adebcdc7b7
|
| 3 |
+
size 986047904
|
german-ocr-3.1-Q8_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2159e9bfc6e7c3cd1be5043f469824a370f8a73d5d522555a7e7844e88d6593e
|
| 3 |
+
size 1646572416
|
mmproj-german-ocr-3.1-F16.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17b642535eda345b2316d1545e2caad34418b14a991f1708e719f1c322f24a01
|
| 3 |
+
size 1331656544
|