Instructions to use harryrobert/latexOCR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use harryrobert/latexOCR with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="harryrobert/latexOCR", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("harryrobert/latexOCR", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use harryrobert/latexOCR with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "harryrobert/latexOCR" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "harryrobert/latexOCR", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/harryrobert/latexOCR
- SGLang
How to use harryrobert/latexOCR 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 "harryrobert/latexOCR" \ --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": "harryrobert/latexOCR", "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 "harryrobert/latexOCR" \ --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": "harryrobert/latexOCR", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use harryrobert/latexOCR with Docker Model Runner:
docker model run hf.co/harryrobert/latexOCR
Upload config.json with huggingface_hub
Browse files- config.json +23 -0
config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "latex_decoder",
|
| 3 |
+
"architectures": ["LaTeXDecoderForCausalLM"],
|
| 4 |
+
"auto_map": {
|
| 5 |
+
"AutoConfig": "configuration_latex_decoder.LaTeXDecoderConfig",
|
| 6 |
+
"AutoModelForCausalLM": "modeling_latex_decoder.LaTeXDecoderForCausalLM"
|
| 7 |
+
},
|
| 8 |
+
"vocab_size": 8192,
|
| 9 |
+
"pad_id": 0,
|
| 10 |
+
"bos_id": 2,
|
| 11 |
+
"eos_id": 3,
|
| 12 |
+
"pad_token_id": 0,
|
| 13 |
+
"bos_token_id": 2,
|
| 14 |
+
"eos_token_id": 3,
|
| 15 |
+
"d_model": 512,
|
| 16 |
+
"n_heads": 8,
|
| 17 |
+
"n_layers": 6,
|
| 18 |
+
"d_ff": 1408,
|
| 19 |
+
"dropout": 0.1,
|
| 20 |
+
"max_seq_len": 200,
|
| 21 |
+
"rope_theta": 10000.0,
|
| 22 |
+
"tie_weights": true
|
| 23 |
+
}
|