Instructions to use q-future/co-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use q-future/co-instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="q-future/co-instruct", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("q-future/co-instruct", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use q-future/co-instruct with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "q-future/co-instruct" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "q-future/co-instruct", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/q-future/co-instruct
- SGLang
How to use q-future/co-instruct 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 "q-future/co-instruct" \ --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": "q-future/co-instruct", "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 "q-future/co-instruct" \ --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": "q-future/co-instruct", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use q-future/co-instruct with Docker Model Runner:
docker model run hf.co/q-future/co-instruct
Upload modeling_mplug_owl2.py with huggingface_hub
Browse files- modeling_mplug_owl2.py +1 -1
modeling_mplug_owl2.py
CHANGED
|
@@ -272,7 +272,7 @@ class MPLUGOwl2LlamaForCausalLM(LlamaForCausalLM, MPLUGOwl2MetaForCausalLM):
|
|
| 272 |
images = [expand2square(img, tuple(int(x*255) for x in self.image_processor.image_mean)) for img in images]
|
| 273 |
image_tensor = self.image_processor.preprocess(images, return_tensors="pt")["pixel_values"].half().to(self.device)
|
| 274 |
|
| 275 |
-
return self.
|
| 276 |
def score(self, images,
|
| 277 |
task_: str = "quality",
|
| 278 |
input_: str = "image",
|
|
|
|
| 272 |
images = [expand2square(img, tuple(int(x*255) for x in self.image_processor.image_mean)) for img in images]
|
| 273 |
image_tensor = self.image_processor.preprocess(images, return_tensors="pt")["pixel_values"].half().to(self.device)
|
| 274 |
|
| 275 |
+
return self.generate(input_ids, images=image_tensor, streamer=self.streamer, **generate_kwargs)
|
| 276 |
def score(self, images,
|
| 277 |
task_: str = "quality",
|
| 278 |
input_: str = "image",
|