RWKV7 Goose World3 1.5B HF

🚀 rwkv7-1.47B-pile

This is an RWKV-7 model under the flash-linear attention format, designed for text generation tasks.

🚀 Quick Start

Before using this model, you need to install flash-linear-attention <= 0.1.2 and the latest version of transformers:

pip install --no-use-pep517 flash-linear-attention==0.1.2
pip install 'transformers>=4.48.0'

✨ Features

This is an RWKV-7 model under the flash-linear attention format, which can be used for text generation tasks just like other HuggingFace models.

📦 Installation

Install flash-linear-attention <= 0.1.2 and the latest version of transformers:

pip install --no-use-pep517 flash-linear-attention==0.1.2
pip install 'transformers>=4.48.0'

💻 Usage Examples

Basic Usage

You can use this model just as any other HuggingFace models:

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained('fla-hub/rwkv7-1.47B-pile', trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained('fla-hub/rwkv7-1.47B-pile', trust_remote_code=True)

📚 Documentation

Model Details

Model Description

• Developed by: Bo Peng, Yu Zhang, Songlin Yang, Ruichong Zhang
• Funded by: RWKV Project (Under LF AI & Data Foundation)
• Model type: RWKV7
• Language(s) (NLP): English
• License: Apache-2.0
• Parameter count: 1.47B
• Tokenizer: GPT-NeoX 20B tokenizer

Model Sources

• Repository: https://github.com/fla-org/flash-linear-attention ; https://github.com/BlinkDL/RWKV-LM
• Paper: RWKV-7 "Goose" with Expressive Dynamic State Evolution

Training Details

Training Data

This model is trained on the Pile with a total of 332 billion tokens.

Evaluation

Metrics

lambada_openai: ppl 4.80 acc 67.0% piqa: acc 73.5%

FAQ

Q: safetensors metadata is none. A: upgrade transformers to >=4.48.0: pip install 'transformers>=4.48.0'

📄 License

This model is licensed under the Apache-2.0 license.