Instructions to use sherw99/Rex-Anima-M1-110M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sherw99/Rex-Anima-M1-110M with Transformers:

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

pipe = pipeline("text-generation", model="sherw99/Rex-Anima-M1-110M")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sherw99/Rex-Anima-M1-110M")
model = AutoModelForCausalLM.from_pretrained("sherw99/Rex-Anima-M1-110M", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sherw99/Rex-Anima-M1-110M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sherw99/Rex-Anima-M1-110M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sherw99/Rex-Anima-M1-110M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sherw99/Rex-Anima-M1-110M

SGLang

How to use sherw99/Rex-Anima-M1-110M 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 "sherw99/Rex-Anima-M1-110M" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sherw99/Rex-Anima-M1-110M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "sherw99/Rex-Anima-M1-110M" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sherw99/Rex-Anima-M1-110M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sherw99/Rex-Anima-M1-110M with Docker Model Runner:
```
docker model run hf.co/sherw99/Rex-Anima-M1-110M
```

Rex Anima Mark I (110M)

Rex Anima Mark I is a custom-trained conversational model built on the GPT-2 architecture. It features a unique "Soul Layer" fine-tuned for emotional intelligence and empathy.

Model Details

Architecture: GPT-2 (Causal LM)
Parameters: ~125M
Vocabulary Size: 32,000
Special Tokens: Includes emotional identifiers like <emo:joy>, <emo:sadness>, and interaction tokens like [HUMAN], [ANIMA], [EMPATHIZE].

Training Stages

Pre-train: OpenWebText + WikiText-103
Conv Fine-tune: PersonaChat + CounselChat
Emotion Fine-tune: EmpatheticDialogues (Soul Layer)

Downloads last month: 9

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for sherw99/Rex-Anima-M1-110M

Base model

openai-community/gpt2

Finetuned

(2262)

this model