Instructions to use coconut495/glm-ocr-ru-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use coconut495/glm-ocr-ru-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("zai-org/GLM-OCR")
model = PeftModel.from_pretrained(base_model, "coconut495/glm-ocr-ru-lora")

Transformers

How to use coconut495/glm-ocr-ru-lora with Transformers:

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

pipe = pipeline("text-generation", model="coconut495/glm-ocr-ru-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("coconut495/glm-ocr-ru-lora", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use coconut495/glm-ocr-ru-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "coconut495/glm-ocr-ru-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "coconut495/glm-ocr-ru-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/coconut495/glm-ocr-ru-lora

SGLang

How to use coconut495/glm-ocr-ru-lora 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 "coconut495/glm-ocr-ru-lora" \
    --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": "coconut495/glm-ocr-ru-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "coconut495/glm-ocr-ru-lora" \
        --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": "coconut495/glm-ocr-ru-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use coconut495/glm-ocr-ru-lora with Docker Model Runner:
```
docker model run hf.co/coconut495/glm-ocr-ru-lora
```

sft

This model is a fine-tuned version of zai-org/GLM-OCR on the glm_ocr_ru dataset. It achieves the following results on the evaluation set:

Loss: 0.1512

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 0.1
num_epochs: 3.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.2588	0.3370	100	0.2637
0.2077	0.6740	200	0.2093
0.1697	1.0101	300	0.1847
0.1514	1.3471	400	0.1700
0.1446	1.6841	500	0.1614
0.1302	2.0202	600	0.1559
0.1257	2.3572	700	0.1525
0.1266	2.6942	800	0.1514
0.1224	3.0	891	0.1512

Framework versions

PEFT 0.18.1
Transformers 5.12.1
Pytorch 2.11.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2

Downloads last month: 11

Model tree for coconut495/glm-ocr-ru-lora

Base model

zai-org/GLM-OCR

Adapter

(8)

this model