Instructions to use InnerI/synCAI-144k-gpt2.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use InnerI/synCAI-144k-gpt2.5 with Transformers:

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

pipe = pipeline("text-generation", model="InnerI/synCAI-144k-gpt2.5")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("InnerI/synCAI-144k-gpt2.5")
model = AutoModelForCausalLM.from_pretrained("InnerI/synCAI-144k-gpt2.5")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use InnerI/synCAI-144k-gpt2.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "InnerI/synCAI-144k-gpt2.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "InnerI/synCAI-144k-gpt2.5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/InnerI/synCAI-144k-gpt2.5

SGLang

How to use InnerI/synCAI-144k-gpt2.5 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 "InnerI/synCAI-144k-gpt2.5" \
    --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": "InnerI/synCAI-144k-gpt2.5",
		"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 "InnerI/synCAI-144k-gpt2.5" \
        --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": "InnerI/synCAI-144k-gpt2.5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use InnerI/synCAI-144k-gpt2.5 with Docker Model Runner:
```
docker model run hf.co/InnerI/synCAI-144k-gpt2.5
```

⚠ CONSTRUCTION GOING

synCAI-144k-gpt-2.5

Overview

synCAI-144k-gpt-2.5 is a large language model designed to advance AI and consciousness studies. This model is fine-tuned on the InnerI/synCAI_144kda dataset, which contains 144,000 synthetic data points focused on consciousness-related topics.

Training Dataset

The dataset used for fine-tuning is InnerI/synCAI_144kda, available at InnerI/synCAI_144kda. It includes:

10,000 Unique Rows: Diverse questions and responses designed to advance AI and consciousness studies.
144,000 Synthetic Rows: Additional data from Mostly AI, providing a comprehensive training dataset.
also at Mostly AI - https://app.mostly.ai/d/synthetic-datasets/992ddc63-7059-4bb8-8dd8-a7eb2dc7a579

Intended Use

synCAI-144k-gpt-2.5 is intended for AI applications in consciousness studies and large-scale AI tasks. Potential use cases include:

Generating responses to questions about consciousness, covering philosophical, neuroscientific, and quantum topics.
Assisting in AI-based consciousness research and analysis.
Supporting AI training and development with a focus on consciousness-related tasks.

Model Capabilities

synCAI-144k-gpt-2.5 can:

Generate responses to questions about consciousness, drawing from a diverse dataset.
Assist in training AI models for consciousness studies and related applications.
Support AI-based analysis and research in fields focusing on consciousness.

Licensing and Usage

Ensure compliance with any licensing agreements or usage restrictions when using this model. It is intended for academic and research purposes. If you use or share the model, provide appropriate attribution.

Contributing

Contributions to the model are welcome. If you have suggestions for improvements or additional use cases, consider submitting them for review and inclusion.

Contact Information

For further information about the model or additional questions, please contact @innerinetco

Downloads last month: 3

Safetensors

Model size

0.4B params

Tensor type

F32