Instructions to use marutitecblic/HtmlTocode with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use marutitecblic/HtmlTocode with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="marutitecblic/HtmlTocode", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("marutitecblic/HtmlTocode", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use marutitecblic/HtmlTocode with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "marutitecblic/HtmlTocode" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "marutitecblic/HtmlTocode", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/marutitecblic/HtmlTocode
- SGLang
How to use marutitecblic/HtmlTocode 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 "marutitecblic/HtmlTocode" \ --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": "marutitecblic/HtmlTocode", "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 "marutitecblic/HtmlTocode" \ --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": "marutitecblic/HtmlTocode", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use marutitecblic/HtmlTocode with Docker Model Runner:
docker model run hf.co/marutitecblic/HtmlTocode
Update handler.py
Browse files- handler.py +4 -4
handler.py
CHANGED
|
@@ -59,15 +59,15 @@ DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
|
| 59 |
# return response
|
| 60 |
|
| 61 |
class EndpointHandler:
|
| 62 |
-
def __init__(self):
|
| 63 |
# Load processor and model
|
| 64 |
self.PROCESSOR = AutoProcessor.from_pretrained(
|
| 65 |
-
|
| 66 |
trust_remote_code=True,
|
| 67 |
# token=API_TOKEN,
|
| 68 |
)
|
| 69 |
self.MODEL = AutoModelForCausalLM.from_pretrained(
|
| 70 |
-
|
| 71 |
# token=API_TOKEN,
|
| 72 |
trust_remote_code=True,
|
| 73 |
torch_dtype=torch.bfloat16,
|
|
@@ -99,7 +99,7 @@ class EndpointHandler:
|
|
| 99 |
# inputs = preprocess(model_inputs)
|
| 100 |
generated_ids = self.MODEL.generate(**inputs, bad_words_ids=self.BAD_WORDS_IDS, max_length=4096)
|
| 101 |
generated_text = self.PROCESSOR.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
| 102 |
-
return {"
|
| 103 |
# return {"text":prediction[0]}
|
| 104 |
|
| 105 |
# @classmethod
|
|
|
|
| 59 |
# return response
|
| 60 |
|
| 61 |
class EndpointHandler:
|
| 62 |
+
def __init__(self,model_path:str):
|
| 63 |
# Load processor and model
|
| 64 |
self.PROCESSOR = AutoProcessor.from_pretrained(
|
| 65 |
+
model_path,
|
| 66 |
trust_remote_code=True,
|
| 67 |
# token=API_TOKEN,
|
| 68 |
)
|
| 69 |
self.MODEL = AutoModelForCausalLM.from_pretrained(
|
| 70 |
+
model_path,
|
| 71 |
# token=API_TOKEN,
|
| 72 |
trust_remote_code=True,
|
| 73 |
torch_dtype=torch.bfloat16,
|
|
|
|
| 99 |
# inputs = preprocess(model_inputs)
|
| 100 |
generated_ids = self.MODEL.generate(**inputs, bad_words_ids=self.BAD_WORDS_IDS, max_length=4096)
|
| 101 |
generated_text = self.PROCESSOR.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
| 102 |
+
return {"text": generated_text}
|
| 103 |
# return {"text":prediction[0]}
|
| 104 |
|
| 105 |
# @classmethod
|