Image-Text-to-Text
Transformers
Safetensors
German
ocr
vision-language
lightonocr
document-understanding
german
shorthand
manuscript
medieval
conversational
Instructions to use wjbmattingly/LightOnOCR-2-1B-german-shorthand-line with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use wjbmattingly/LightOnOCR-2-1B-german-shorthand-line with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="wjbmattingly/LightOnOCR-2-1B-german-shorthand-line") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("wjbmattingly/LightOnOCR-2-1B-german-shorthand-line", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use wjbmattingly/LightOnOCR-2-1B-german-shorthand-line with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "wjbmattingly/LightOnOCR-2-1B-german-shorthand-line" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "wjbmattingly/LightOnOCR-2-1B-german-shorthand-line", "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/wjbmattingly/LightOnOCR-2-1B-german-shorthand-line
- SGLang
How to use wjbmattingly/LightOnOCR-2-1B-german-shorthand-line with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "wjbmattingly/LightOnOCR-2-1B-german-shorthand-line" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "wjbmattingly/LightOnOCR-2-1B-german-shorthand-line", "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 images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "wjbmattingly/LightOnOCR-2-1B-german-shorthand-line" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "wjbmattingly/LightOnOCR-2-1B-german-shorthand-line", "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" } } ] } ] }' - Docker Model Runner
How to use wjbmattingly/LightOnOCR-2-1B-german-shorthand-line with Docker Model Runner:
docker model run hf.co/wjbmattingly/LightOnOCR-2-1B-german-shorthand-line
Upload folder using huggingface_hub
Browse files- README.md +7 -7
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +0 -0
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -42,8 +42,8 @@ Evaluated on 50 samples from the test set:
|
|
| 42 |
|
| 43 |
| Metric | Base Model | **Finetuned** | Improvement |
|
| 44 |
|--------|------------|---------------|-------------|
|
| 45 |
-
| CER (%) | 381.26 | **
|
| 46 |
-
| WER (%) | 494.99 | **
|
| 47 |
| Perfect Matches | 0 | **0** | +0 |
|
| 48 |
|
| 49 |
*Lower CER/WER is better. Higher perfect matches is better.*
|
|
@@ -52,13 +52,13 @@ Evaluated on 50 samples from the test set:
|
|
| 52 |
|
| 53 |
| # | Ground Truth | Base Model | **Finetuned** |
|
| 54 |
|---|--------------|------------|---------------|
|
| 55 |
-
| 1 | (Haupt der seligen Irmeng. gefunden. Im ... | 12/12/1998 10:00 AM 10:00 AM 10:00 AM 10... | (
|
| 56 |
-
| 2 | Schw. Reinh.: Ist vom Lagerdienst freige... | Schw. Reinh. : 2d 9.20 16 09 J. 6 | Schw.
|
| 57 |
| 3 | Klage daß im Naz.heim den Kranken die Ko... | $$
|
| 58 |
\begin{aligned}
|
| 59 |
-
& \text { 22 e 2 haz.... |
|
| 60 |
-
| 4 | Irene: Stimmung sehr verschieden. Kommen... | | Irene:
|
| 61 |
-
| 5 | Zwei Schwestern Calabrien: M. Cristina u... | 226 *Kolabrie: M. Cisneros, Urode* |
|
| 62 |
|
| 63 |
*✓ = exact match*
|
| 64 |
|
|
|
|
| 42 |
|
| 43 |
| Metric | Base Model | **Finetuned** | Improvement |
|
| 44 |
|--------|------------|---------------|-------------|
|
| 45 |
+
| CER (%) | 381.26 | **21.89** | +359.37 |
|
| 46 |
+
| WER (%) | 494.99 | **37.41** | +457.58 |
|
| 47 |
| Perfect Matches | 0 | **0** | +0 |
|
| 48 |
|
| 49 |
*Lower CER/WER is better. Higher perfect matches is better.*
|
|
|
|
| 52 |
|
| 53 |
| # | Ground Truth | Base Model | **Finetuned** |
|
| 54 |
|---|--------------|------------|---------------|
|
| 55 |
+
| 1 | (Haupt der seligen Irmeng. gefunden. Im ... | 12/12/1998 10:00 AM 10:00 AM 10:00 AM 10... | (Haupt der seitdem Jänner 12 20 bei Daue... |
|
| 56 |
+
| 2 | Schw. Reinh.: Ist vom Lagerdienst freige... | Schw. Reinh. : 2d 9.20 16 09 J. 6 | Schw. Reinh.: Ist vom Lagerdienst frei g... |
|
| 57 |
| 3 | Klage daß im Naz.heim den Kranken die Ko... | $$
|
| 58 |
\begin{aligned}
|
| 59 |
+
& \text { 22 e 2 haz.... | Klage daß im Naz.heim den Kranken die Ko... |
|
| 60 |
+
| 4 | Irene: Stimmung sehr verschieden. Kommen... | | Irene: Stimmung sehr verschiedenes. Münd... |
|
| 61 |
+
| 5 | Zwei Schwestern Calabrien: M. Cristina u... | 226 *Kolabrie: M. Cisneros, Urode* | Zwei Schwestern Katalrien: M. Cristina u... |
|
| 62 |
|
| 63 |
*✓ = exact match*
|
| 64 |
|
adapter_config.json
CHANGED
|
@@ -29,10 +29,10 @@
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
-
"gate_proj",
|
| 33 |
"o_proj",
|
| 34 |
-
"
|
| 35 |
-
"down_proj"
|
|
|
|
| 36 |
],
|
| 37 |
"target_parameters": null,
|
| 38 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
|
|
|
| 32 |
"o_proj",
|
| 33 |
+
"gate_proj",
|
| 34 |
+
"down_proj",
|
| 35 |
+
"up_proj"
|
| 36 |
],
|
| 37 |
"target_parameters": null,
|
| 38 |
"task_type": "CAUSAL_LM",
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 27195864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9a3f7bbcd733b37e7fade8d080afcdb906c992d8f41f25cc929deeb7c33cf4a
|
| 3 |
size 27195864
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 54619587
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39e0446d1b2447d14ae7f9d2c29a06b083607f03d6ea1a9840841c296cfdaf69
|
| 3 |
size 54619587
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a216119dd691a5c4c3cf0919e27729f871b1e66e778348c7af2b1e385a09ffc3
|
| 3 |
size 14645
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fd0298d5a94f9b48cacf7130ace0cb1063b3c6e2d7b8233ce3f128cc30d02e9
|
| 3 |
size 1465
|
trainer_state.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5201
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a60cb8bedd244cb81ccf2137e14e0c6d5b71ccad42c31d4e1482adf4b34ccde3
|
| 3 |
size 5201
|