Instructions to use Kowsher/TokenTrails with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Kowsher/TokenTrails with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Kowsher/TokenTrails", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Kowsher/TokenTrails", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("Kowsher/TokenTrails", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Kowsher/TokenTrails with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Kowsher/TokenTrails" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Kowsher/TokenTrails", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Kowsher/TokenTrails
- SGLang
How to use Kowsher/TokenTrails 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 "Kowsher/TokenTrails" \ --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": "Kowsher/TokenTrails", "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 "Kowsher/TokenTrails" \ --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": "Kowsher/TokenTrails", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Kowsher/TokenTrails with Docker Model Runner:
docker model run hf.co/Kowsher/TokenTrails
Update handler.py
Browse files- handler.py +5 -3
handler.py
CHANGED
|
@@ -1,16 +1,18 @@
|
|
| 1 |
import torch
|
| 2 |
|
| 3 |
from typing import Any, Dict
|
| 4 |
-
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 5 |
from transformers.models.auto import modeling_auto
|
| 6 |
|
| 7 |
|
| 8 |
class EndpointHandler:
|
| 9 |
def __init__(self, path=""):
|
|
|
|
|
|
|
| 10 |
# load model and tokenizer from path
|
| 11 |
-
self.tokenizer = AutoTokenizer.from_pretrained(path)
|
| 12 |
self.model = AutoModelForCausalLM.from_pretrained(
|
| 13 |
-
path, device_map="auto", torch_dtype=torch.float16, trust_remote_code=True
|
| 14 |
)
|
| 15 |
self.device = "cuda" if torch.cuda.is_available() else "cpu"
|
| 16 |
|
|
|
|
| 1 |
import torch
|
| 2 |
|
| 3 |
from typing import Any, Dict
|
| 4 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer, AutoConfig
|
| 5 |
from transformers.models.auto import modeling_auto
|
| 6 |
|
| 7 |
|
| 8 |
class EndpointHandler:
|
| 9 |
def __init__(self, path=""):
|
| 10 |
+
print('starting machine')
|
| 11 |
+
config = AutoConfig.from_pretrained("Kowsher/Egol_model", trust_remote_code=True)
|
| 12 |
# load model and tokenizer from path
|
| 13 |
+
self.tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)
|
| 14 |
self.model = AutoModelForCausalLM.from_pretrained(
|
| 15 |
+
path, device_map="auto", torch_dtype=torch.float16, config = config, trust_remote_code=True
|
| 16 |
)
|
| 17 |
self.device = "cuda" if torch.cuda.is_available() else "cpu"
|
| 18 |
|