Image-to-Text
Transformers
Safetensors
Samaritan
Samaritan Aramaic
glm_ocr
image-text-to-text
ocr
samaritan
ancient-languages
vision
glm-ocr
Instructions to use johnlockejrr/GLM-OCR-samaritan with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use johnlockejrr/GLM-OCR-samaritan with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="johnlockejrr/GLM-OCR-samaritan", device_map="auto")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("johnlockejrr/GLM-OCR-samaritan") model = AutoModelForMultimodalLM.from_pretrained("johnlockejrr/GLM-OCR-samaritan", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| # ollama modelfile auto-generated by llamafactory | |
| FROM . | |
| TEMPLATE """[gMASK]<sop>{{ if .System }}<|system|> | |
| {{ .System }}{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<|user|> | |
| {{ .Content }}<|assistant|>{{ else if eq .Role "assistant" }} | |
| {{ .Content }}{{ end }}{{ end }}""" | |
| PARAMETER stop "<|user|>" | |
| PARAMETER stop "<|endoftext|>" | |
| PARAMETER stop "<|observation|>" | |
| PARAMETER num_ctx 4096 | |