Instructions to use dmayhem93/RandomWalkADC_v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dmayhem93/RandomWalkADC_v0 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="dmayhem93/RandomWalkADC_v0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dmayhem93/RandomWalkADC_v0")
model = AutoModelForCausalLM.from_pretrained("dmayhem93/RandomWalkADC_v0")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use dmayhem93/RandomWalkADC_v0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dmayhem93/RandomWalkADC_v0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dmayhem93/RandomWalkADC_v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/dmayhem93/RandomWalkADC_v0

SGLang

How to use dmayhem93/RandomWalkADC_v0 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 "dmayhem93/RandomWalkADC_v0" \
    --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": "dmayhem93/RandomWalkADC_v0",
		"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 "dmayhem93/RandomWalkADC_v0" \
        --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": "dmayhem93/RandomWalkADC_v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dmayhem93/RandomWalkADC_v0 with Docker Model Runner:
```
docker model run hf.co/dmayhem93/RandomWalkADC_v0
```

dmayhem93 commited on Mar 9, 2023

Commit

4241bad

1 Parent(s): de0b576

update

Browse files

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -8,7 +8,8 @@ which we will randomly reject and go to the next highest comment. This repeats u
 We sample the reply chain in this manner until we do not have any more replies to the current comment.
 The input to the model will look something like this:
-```ExampleUser
 Example Title
 Example Comment <BACKGROUND_INDEX_TOKEN> Other_User
 Edit: Second <REJECTED_UTTERANCE> First_User

 We sample the reply chain in this manner until we do not have any more replies to the current comment.
 The input to the model will look something like this:
+```
+ExampleUser
 Example Title
 Example Comment <BACKGROUND_INDEX_TOKEN> Other_User
 Edit: Second <REJECTED_UTTERANCE> First_User