Instructions to use not-lain/finetuned_deepseek_ocr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use not-lain/finetuned_deepseek_ocr with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-OCR")
model = PeftModel.from_pretrained(base_model, "not-lain/finetuned_deepseek_ocr")

Transformers

How to use not-lain/finetuned_deepseek_ocr with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="not-lain/finetuned_deepseek_ocr", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("not-lain/finetuned_deepseek_ocr", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use not-lain/finetuned_deepseek_ocr with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "not-lain/finetuned_deepseek_ocr"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "not-lain/finetuned_deepseek_ocr",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/not-lain/finetuned_deepseek_ocr

SGLang

How to use not-lain/finetuned_deepseek_ocr 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 "not-lain/finetuned_deepseek_ocr" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "not-lain/finetuned_deepseek_ocr",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "not-lain/finetuned_deepseek_ocr" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "not-lain/finetuned_deepseek_ocr",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use not-lain/finetuned_deepseek_ocr with Docker Model Runner:
```
docker model run hf.co/not-lain/finetuned_deepseek_ocr
```

not-lain commited on Oct 30, 2025

Commit

c2da129

verified ·

1 Parent(s): 5428fa2

not-lain/finetuned_deepseek_ocr

Browse files

Files changed (3) hide show

README.md +11 -5
adapter_model.safetensors +1 -1
runs/Oct30_17-20-43_368ad1980789/events.out.tfevents.1761844845.368ad1980789.6156.5 +2 -2

README.md CHANGED Viewed

@@ -1,9 +1,14 @@
 ---
-library_name: transformers
 license: mit
 base_model: deepseek-ai/DeepSeek-OCR
 tags:
-- generated_from_trainer
 model-index:
 - name: finetuned_deepseek_ocr
   results: []
@@ -34,12 +39,12 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 0.0005
-- train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- training_steps: 3
 ### Training results
@@ -47,7 +52,8 @@ The following hyperparameters were used during training:
 ### Framework versions
 - Transformers 4.46.3
 - Pytorch 2.6.0+cu124
 - Datasets 4.3.0
-- Tokenizers 0.20.3

 ---
+library_name: peft
 license: mit
 base_model: deepseek-ai/DeepSeek-OCR
 tags:
+- base_model:adapter:deepseek-ai/DeepSeek-OCR
+- lora
+- sft
+- transformers
+- trl
+pipeline_tag: text-generation
 model-index:
 - name: finetuned_deepseek_ocr
   results: []
 The following hyperparameters were used during training:
 - learning_rate: 0.0005
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
+- training_steps: 8
 ### Training results
 ### Framework versions
+- PEFT 0.17.1
 - Transformers 4.46.3
 - Pytorch 2.6.0+cu124
 - Datasets 4.3.0
+- Tokenizers 0.20.3

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b286d1de8ead082ffe7f4d74bdb4fa3570ae09031c382169ecab15c1f03bb9dd
 size 2958552

 version https://git-lfs.github.com/spec/v1
+oid sha256:5b495ec84536d6424b2d80c560fe16eb1ffd638e871c98668ce4f122f8115bec
 size 2958552

runs/Oct30_17-20-43_368ad1980789/events.out.tfevents.1761844845.368ad1980789.6156.5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4861e14d1685ec7b7d5a1534232b5a82654c6e95ffcfca427dfcc6035550041f
-size 9149

 version https://git-lfs.github.com/spec/v1
+oid sha256:31c15e392639fc44aecc2ad2c096a2535a7e19148e27e655a40f4b890fc3bc75
+size 9704