Instructions to use aduncan94/EnhancAR-Sorted with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aduncan94/EnhancAR-Sorted with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="aduncan94/EnhancAR-Sorted")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aduncan94/EnhancAR-Sorted")
model = AutoModelForCausalLM.from_pretrained("aduncan94/EnhancAR-Sorted")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use aduncan94/EnhancAR-Sorted with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aduncan94/EnhancAR-Sorted"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aduncan94/EnhancAR-Sorted",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/aduncan94/EnhancAR-Sorted

SGLang

How to use aduncan94/EnhancAR-Sorted 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 "aduncan94/EnhancAR-Sorted" \
    --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": "aduncan94/EnhancAR-Sorted",
		"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 "aduncan94/EnhancAR-Sorted" \
        --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": "aduncan94/EnhancAR-Sorted",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use aduncan94/EnhancAR-Sorted with Docker Model Runner:
```
docker model run hf.co/aduncan94/EnhancAR-Sorted
```

aduncan94 commited on Apr 10

Commit

0d880d2

verified ·

1 Parent(s): b1c7433

Update README.md

Browse files

Files changed (1) hide show

README.md +26 -3

README.md CHANGED Viewed

@@ -30,12 +30,36 @@ EnhancAR-sorted is a generative enhancer model that can be used for:
 ## Getting Started with EnhancAR-Sorted
 **Requirements**:
-* PyTorch:
-* CUDA:
 **Example generation**:
 ```py
 ```
 ## Technical Specifications
@@ -46,4 +70,3 @@ EnhancAR-sorted is a generative enhancer model that can be used for:
 ## Citation
 If you use the code, models, or results, please cite our [preprint]()
-*

 ## Getting Started with EnhancAR-Sorted
 **Requirements**:
+* PyTorch: 2.7.1
+* CUDA: 12.8 and above
+```py
+pip install transformers==4.48.2 huggingface_hub
+```
 **Example generation**:
+The following shows an example for generating an unconditional sequence. To generate a sequence conditionally, replace the input_sequence with a string of the form:
+{homolog A/homolog B/.../homolog N}.
+For a full example, please see the [Google Colab]()
 ```py
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, AutoConfig
+config = AutoConfig.from_pretrained("aduncan94/EnhancAR-Sorted", trust_remote_code=True)
+config.use_mamba_kernels = False
+model = AutoModelForCausalLM.from_pretrained("aduncan94/EnhancAR-Sorted", trust_remote_code=True, config=config).to("cuda")
+tokenizer = AutoTokenizer.from_pretrained("aduncan94/EnhancAR-Sorted", trust_remote_code=True)
+input_sequence = "{"
+inputs = tokenizer(input_sequence, return_tensors="pt", return_token_type_ids=False, add_special_tokens=False)
+outputs = generate_sequence(inputs, model, tokenizer)
+output = tokenizer.batch_decode(outputs, skip_special_tokens=False)[0]
+print(output)
 ```
 ## Technical Specifications
 ## Citation
 If you use the code, models, or results, please cite our [preprint]()