Text Generation
Transformers
PyTorch
Safetensors
English
Sparrow
endpoints
text-generation-inference
custom_code
Instructions to use ManishThota/CustomModel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ManishThota/CustomModel with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ManishThota/CustomModel", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("ManishThota/CustomModel", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use ManishThota/CustomModel with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ManishThota/CustomModel" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ManishThota/CustomModel", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ManishThota/CustomModel
- SGLang
How to use ManishThota/CustomModel 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 "ManishThota/CustomModel" \ --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": "ManishThota/CustomModel", "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 "ManishThota/CustomModel" \ --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": "ManishThota/CustomModel", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ManishThota/CustomModel with Docker Model Runner:
docker model run hf.co/ManishThota/CustomModel
Update README.md
Browse files
README.md
CHANGED
|
@@ -31,11 +31,11 @@ torch.set_default_device("cuda")
|
|
| 31 |
|
| 32 |
#Create model
|
| 33 |
model = AutoModelForCausalLM.from_pretrained(
|
| 34 |
-
"ManishThota/
|
| 35 |
torch_dtype=torch.float16,
|
| 36 |
device_map="auto",
|
| 37 |
trust_remote_code=True)
|
| 38 |
-
tokenizer = AutoTokenizer.from_pretrained("ManishThota/
|
| 39 |
|
| 40 |
#function to generate the answer
|
| 41 |
def predict(question, image_path):
|
|
|
|
| 31 |
|
| 32 |
#Create model
|
| 33 |
model = AutoModelForCausalLM.from_pretrained(
|
| 34 |
+
"ManishThota/CustomModel",
|
| 35 |
torch_dtype=torch.float16,
|
| 36 |
device_map="auto",
|
| 37 |
trust_remote_code=True)
|
| 38 |
+
tokenizer = AutoTokenizer.from_pretrained("ManishThota/CustomModel", trust_remote_code=True)
|
| 39 |
|
| 40 |
#function to generate the answer
|
| 41 |
def predict(question, image_path):
|