Image-Text-to-Text
Transformers
Safetensors
English
opencua
feature-extraction
VLM
Computer-Use-Agent
OS-Agent
GUI
Grounding
conversational
custom_code
4-bit precision
bitsandbytes
Instructions to use sujitvasanth/OpenCUA7BQfp164bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sujitvasanth/OpenCUA7BQfp164bit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="sujitvasanth/OpenCUA7BQfp164bit", trust_remote_code=True) messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("sujitvasanth/OpenCUA7BQfp164bit", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use sujitvasanth/OpenCUA7BQfp164bit with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "sujitvasanth/OpenCUA7BQfp164bit" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "sujitvasanth/OpenCUA7BQfp164bit", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/sujitvasanth/OpenCUA7BQfp164bit
- SGLang
How to use sujitvasanth/OpenCUA7BQfp164bit 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 "sujitvasanth/OpenCUA7BQfp164bit" \ --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": "sujitvasanth/OpenCUA7BQfp164bit", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'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 "sujitvasanth/OpenCUA7BQfp164bit" \ --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": "sujitvasanth/OpenCUA7BQfp164bit", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use sujitvasanth/OpenCUA7BQfp164bit with Docker Model Runner:
docker model run hf.co/sujitvasanth/OpenCUA7BQfp164bit
Upload modeling_opencua.py
Browse files2 small changesa to work with newer transformers libraries (old value is commented out)
@property
def _supports_sdpa(self):
return True #self.language_model._supports_sdpa
----
if past_key_values is not None:
if isinstance(past_key_values, Cache):
cache_length = past_key_values.get_seq_length()
past_length = cache_length # past_key_values.seen_tokens
--------
- modeling_opencua.py +2 -2
modeling_opencua.py
CHANGED
|
@@ -94,7 +94,7 @@ class OpenCUAPreTrainedModel(PreTrainedModel):
|
|
| 94 |
Retrieve language_model's attribute to check whether the model supports
|
| 95 |
SDPA or not.
|
| 96 |
"""
|
| 97 |
-
return self.language_model._supports_sdpa
|
| 98 |
|
| 99 |
|
| 100 |
class OpenCUAForConditionalGeneration(OpenCUAPreTrainedModel):
|
|
@@ -397,7 +397,7 @@ class OpenCUAForConditionalGeneration(OpenCUAPreTrainedModel):
|
|
| 397 |
if past_key_values is not None:
|
| 398 |
if isinstance(past_key_values, Cache):
|
| 399 |
cache_length = past_key_values.get_seq_length()
|
| 400 |
-
past_length = past_key_values.seen_tokens
|
| 401 |
else:
|
| 402 |
cache_length = past_length = past_key_values[0][0].shape[2]
|
| 403 |
|
|
|
|
| 94 |
Retrieve language_model's attribute to check whether the model supports
|
| 95 |
SDPA or not.
|
| 96 |
"""
|
| 97 |
+
return True #self.language_model._supports_sdpa
|
| 98 |
|
| 99 |
|
| 100 |
class OpenCUAForConditionalGeneration(OpenCUAPreTrainedModel):
|
|
|
|
| 397 |
if past_key_values is not None:
|
| 398 |
if isinstance(past_key_values, Cache):
|
| 399 |
cache_length = past_key_values.get_seq_length()
|
| 400 |
+
past_length = cache_length # past_key_values.seen_tokens
|
| 401 |
else:
|
| 402 |
cache_length = past_length = past_key_values[0][0].shape[2]
|
| 403 |
|