Instructions to use Kowsher/TokenTrails with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

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)

# pip install -U transformers accelerate
# 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, device_map="auto")

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
```

Kowsher commited on Jul 18, 2023

Commit

8e4e321

1 Parent(s): cca9ba8

Update handler.py

Browse files

Files changed (1) hide show

handler.py +2 -1

handler.py CHANGED Viewed

@@ -22,7 +22,7 @@ class EndpointHandler:
         # preprocess
         print(print("inputs......", inputs))
         inputs = self.tokenizer(inputs, return_tensors="pt").to(self.device)
-        print("inputs......", inputs)
@@ -36,6 +36,7 @@ class EndpointHandler:
         # pass inputs with all kwargs in data
         if parameters is not None:
             outputs = self.model.generate(**inputs, **parameters)
         else:

         # preprocess
         print(print("inputs......", inputs))
         inputs = self.tokenizer(inputs, return_tensors="pt").to(self.device)
         # pass inputs with all kwargs in data
+        print("inputs......", inputs)
         if parameters is not None:
             outputs = self.model.generate(**inputs, **parameters)
         else: