Instructions to use microsoft/kosmos-2.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/kosmos-2.5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="microsoft/kosmos-2.5")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("microsoft/kosmos-2.5") model = AutoModelForImageTextToText.from_pretrained("microsoft/kosmos-2.5") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use microsoft/kosmos-2.5 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "microsoft/kosmos-2.5" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "microsoft/kosmos-2.5", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/microsoft/kosmos-2.5
- SGLang
How to use microsoft/kosmos-2.5 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 "microsoft/kosmos-2.5" \ --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": "microsoft/kosmos-2.5", "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 "microsoft/kosmos-2.5" \ --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": "microsoft/kosmos-2.5", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use microsoft/kosmos-2.5 with Docker Model Runner:
docker model run hf.co/microsoft/kosmos-2.5
ydshieh commited on
Commit ·
6d11b0d
1
Parent(s): b9b6785
update after integration
Browse files
md.py
CHANGED
|
@@ -11,7 +11,7 @@ model = Kosmos2_5ForConditionalGeneration.from_pretrained(repo, device_map=devic
|
|
| 11 |
processor = AutoProcessor.from_pretrained(repo)
|
| 12 |
|
| 13 |
# sample image
|
| 14 |
-
url = "https://huggingface.co/microsoft/kosmos-2.5/
|
| 15 |
image = Image.open(requests.get(url, stream=True).raw)
|
| 16 |
|
| 17 |
prompt = "<md>"
|
|
@@ -30,4 +30,4 @@ generated_ids = model.generate(
|
|
| 30 |
)
|
| 31 |
|
| 32 |
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)
|
| 33 |
-
print(generated_text[0])
|
|
|
|
| 11 |
processor = AutoProcessor.from_pretrained(repo)
|
| 12 |
|
| 13 |
# sample image
|
| 14 |
+
url = "https://huggingface.co/microsoft/kosmos-2.5/resolve/main/receipt_00008.png"
|
| 15 |
image = Image.open(requests.get(url, stream=True).raw)
|
| 16 |
|
| 17 |
prompt = "<md>"
|
|
|
|
| 30 |
)
|
| 31 |
|
| 32 |
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)
|
| 33 |
+
print(generated_text[0])
|
ocr.py
CHANGED
|
@@ -11,7 +11,7 @@ model = Kosmos2_5ForConditionalGeneration.from_pretrained(repo, device_map=devic
|
|
| 11 |
processor = AutoProcessor.from_pretrained(repo)
|
| 12 |
|
| 13 |
# sample image
|
| 14 |
-
url = "https://huggingface.co/microsoft/kosmos-2.5/
|
| 15 |
image = Image.open(requests.get(url, stream=True).raw)
|
| 16 |
|
| 17 |
# bs = 1
|
|
@@ -70,4 +70,4 @@ for line in lines:
|
|
| 70 |
continue
|
| 71 |
line = list(map(int, line[:8]))
|
| 72 |
draw.polygon(line, outline="red")
|
| 73 |
-
image.save("output.png")
|
|
|
|
| 11 |
processor = AutoProcessor.from_pretrained(repo)
|
| 12 |
|
| 13 |
# sample image
|
| 14 |
+
url = "https://huggingface.co/microsoft/kosmos-2.5/resolve/main/receipt_00008.png"
|
| 15 |
image = Image.open(requests.get(url, stream=True).raw)
|
| 16 |
|
| 17 |
# bs = 1
|
|
|
|
| 70 |
continue
|
| 71 |
line = list(map(int, line[:8]))
|
| 72 |
draw.polygon(line, outline="red")
|
| 73 |
+
image.save("output.png")
|