Instructions to use senga-ml/dnote-body with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use senga-ml/dnote-body with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="senga-ml/dnote-body")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("senga-ml/dnote-body") model = AutoModelForImageTextToText.from_pretrained("senga-ml/dnote-body") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use senga-ml/dnote-body with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "senga-ml/dnote-body" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "senga-ml/dnote-body", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/senga-ml/dnote-body
- SGLang
How to use senga-ml/dnote-body 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 "senga-ml/dnote-body" \ --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": "senga-ml/dnote-body", "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 "senga-ml/dnote-body" \ --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": "senga-ml/dnote-body", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use senga-ml/dnote-body with Docker Model Runner:
docker model run hf.co/senga-ml/dnote-body
Training done
Browse files- preprocessor_config.json +2 -2
- tokenizer.json +2 -2
preprocessor_config.json
CHANGED
|
@@ -20,7 +20,7 @@
|
|
| 20 |
"resample": 2,
|
| 21 |
"rescale_factor": 0.00392156862745098,
|
| 22 |
"size": [
|
| 23 |
-
|
| 24 |
-
|
| 25 |
]
|
| 26 |
}
|
|
|
|
| 20 |
"resample": 2,
|
| 21 |
"rescale_factor": 0.00392156862745098,
|
| 22 |
"size": [
|
| 23 |
+
2560,
|
| 24 |
+
1920
|
| 25 |
]
|
| 26 |
}
|
tokenizer.json
CHANGED
|
@@ -2,13 +2,13 @@
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
-
"max_length":
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
"padding": {
|
| 10 |
"strategy": {
|
| 11 |
-
"Fixed":
|
| 12 |
},
|
| 13 |
"direction": "Right",
|
| 14 |
"pad_to_multiple_of": null,
|
|
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
+
"max_length": 1536,
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
"padding": {
|
| 10 |
"strategy": {
|
| 11 |
+
"Fixed": 1536
|
| 12 |
},
|
| 13 |
"direction": "Right",
|
| 14 |
"pad_to_multiple_of": null,
|