Instructions to use Differentiable/twitch-simulator-filian-neo-125M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Differentiable/twitch-simulator-filian-neo-125M with Transformers:

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

pipe = pipeline("text-generation", model="Differentiable/twitch-simulator-filian-neo-125M")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Differentiable/twitch-simulator-filian-neo-125M")
model = AutoModelForCausalLM.from_pretrained("Differentiable/twitch-simulator-filian-neo-125M", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Differentiable/twitch-simulator-filian-neo-125M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Differentiable/twitch-simulator-filian-neo-125M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Differentiable/twitch-simulator-filian-neo-125M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Differentiable/twitch-simulator-filian-neo-125M

SGLang

How to use Differentiable/twitch-simulator-filian-neo-125M 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 "Differentiable/twitch-simulator-filian-neo-125M" \
    --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": "Differentiable/twitch-simulator-filian-neo-125M",
		"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 "Differentiable/twitch-simulator-filian-neo-125M" \
        --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": "Differentiable/twitch-simulator-filian-neo-125M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Differentiable/twitch-simulator-filian-neo-125M with Docker Model Runner:
```
docker model run hf.co/Differentiable/twitch-simulator-filian-neo-125M
```

Description

This is my first attempt to simulate the Filian's Twitch stream chat based on scraped data. The model is a fine-tuning of GPT-Neo for 125M parameters. The model was able to be trained within 30 minutes on a GTX 1650 with Pytorch's memory pinning feature to share the local RAM with the GPU.

Usage

Make sure to include the prefix "STREAMER: " at the end of the prompt or anywhere the response of the streamer is supposed to go. "Chat messages" are prepend with the "CHAT: " keyword. In case the Hosted Inference API (text box on the side) gets too little text, just keep pressing "Compute" until the sentence ends.

Prompt examples

CHAT: You're cringe
CHAT: KEKW
STREAMER:

CHAT: Are you a Filipino boy?
STREAMER:

CHAT: Hello
CHAT: KEKW Filian is cringe
STREAMER:

Using the keyword "STREAM TITLE" will attempt to replicate the name of a stream:

STREAM TITLE:

You can also induce the streamer to say something by adding a few words of your own at the beginning:

STREAM: Today we will

Downloads last month: 41

Differentiable
/

twitch-simulator-filian-neo-125M

Description

Usage

Prompt examples

Dataset used to train Differentiable/twitch-simulator-filian-neo-125M