Instructions to use nightdessert/WeCheck with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nightdessert/WeCheck with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="nightdessert/WeCheck")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("nightdessert/WeCheck") model = AutoModelForSequenceClassification.from_pretrained("nightdessert/WeCheck") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use nightdessert/WeCheck with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "nightdessert/WeCheck" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nightdessert/WeCheck", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/nightdessert/WeCheck
- SGLang
How to use nightdessert/WeCheck 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 "nightdessert/WeCheck" \ --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": "nightdessert/WeCheck", "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 "nightdessert/WeCheck" \ --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": "nightdessert/WeCheck", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use nightdessert/WeCheck with Docker Model Runner:
docker model run hf.co/nightdessert/WeCheck
Commit ·
2ea844f
1
Parent(s): 7757033
Update README.md
Browse files
README.md
CHANGED
|
@@ -27,8 +27,8 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
|
|
| 27 |
model = AutoModelForSequenceClassification.from_pretrained(model_name)
|
| 28 |
premise = "I first thought that I liked the movie, but upon second thought it was actually disappointing." # Input for Summarization/ Dialogue / Paraphrase
|
| 29 |
hypothesis = "The movie was not good." # Output for Summarization/ Dialogue / Paraphrase
|
| 30 |
-
input = tokenizer(premise, hypothesis, truncation=True, return_tensors="pt")
|
| 31 |
-
output = model(input["input_ids"].to(device))[:,0] # device = "cuda:0" or "cpu"
|
| 32 |
prediction = torch.sigmoid(output).tolist()
|
| 33 |
print(prediction)
|
| 34 |
```
|
|
|
|
| 27 |
model = AutoModelForSequenceClassification.from_pretrained(model_name)
|
| 28 |
premise = "I first thought that I liked the movie, but upon second thought it was actually disappointing." # Input for Summarization/ Dialogue / Paraphrase
|
| 29 |
hypothesis = "The movie was not good." # Output for Summarization/ Dialogue / Paraphrase
|
| 30 |
+
input = tokenizer(premise, hypothesis, truncation=True, return_tensors="pt", truncation_strategy="only_first", max_length=512)
|
| 31 |
+
output = model(input["input_ids"].to(device))['logits'][:,0] # device = "cuda:0" or "cpu"
|
| 32 |
prediction = torch.sigmoid(output).tolist()
|
| 33 |
print(prediction)
|
| 34 |
```
|