Instructions to use MrD05/pyg6b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MrD05/pyg6b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MrD05/pyg6b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("MrD05/pyg6b") model = AutoModelForCausalLM.from_pretrained("MrD05/pyg6b") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use MrD05/pyg6b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MrD05/pyg6b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MrD05/pyg6b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MrD05/pyg6b
- SGLang
How to use MrD05/pyg6b 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 "MrD05/pyg6b" \ --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": "MrD05/pyg6b", "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 "MrD05/pyg6b" \ --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": "MrD05/pyg6b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MrD05/pyg6b with Docker Model Runner:
docker model run hf.co/MrD05/pyg6b
Update handler.py
Browse files- handler.py +2 -2
handler.py
CHANGED
|
@@ -23,9 +23,9 @@ Alice Gate: *Alice strides into the room with a smile, her eyes lighting up when
|
|
| 23 |
class EndpointHandler():
|
| 24 |
|
| 25 |
def __init__(self, path = ""):
|
| 26 |
-
self.tokenizer = AutoTokenizer.from_pretrained(
|
| 27 |
self.model = AutoModelForCausalLM.from_pretrained(
|
| 28 |
-
|
| 29 |
device_map = "auto",
|
| 30 |
load_in_8bit = True,
|
| 31 |
)
|
|
|
|
| 23 |
class EndpointHandler():
|
| 24 |
|
| 25 |
def __init__(self, path = ""):
|
| 26 |
+
self.tokenizer = AutoTokenizer.from_pretrained(path)
|
| 27 |
self.model = AutoModelForCausalLM.from_pretrained(
|
| 28 |
+
path,
|
| 29 |
device_map = "auto",
|
| 30 |
load_in_8bit = True,
|
| 31 |
)
|