Hebrew Gemma 11B V2

🚀 Hebrew-Gemma-11B-V2

An updated version of Hebrew-Gemma-11B that was trained longer and had some bugs fixed. This is an open - source Large Language Model (LLM), a Hebrew/English pretrained generative text model with 11 billion parameters, based on the Gemma - 7B architecture from Google.

🚀 Quick Start

First, ensure you have installed the transformers library. You can install or update it using the following command:

pip install -U transformers

Then, you can choose the appropriate code snippet according to your needs.

💻 Usage Examples

Basic Usage

Running on CPU

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yam-peleg/Hebrew-Gemma-11B-V2")
model = AutoModelForCausalLM.from_pretrained("yam-peleg/Hebrew-Gemma-11B-V2")

input_text = "שלום! מה שלומך היום?"
input_ids = tokenizer(input_text, return_tensors="pt")

outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))

Running on GPU

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yam-peleg/Hebrew-Gemma-11B-V2")
model = AutoModelForCausalLM.from_pretrained("yam-peleg/Hebrew-Gemma-11B-V2", device_map="auto")

input_text = "שלום! מה שלומך היום?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))

Running with 4 - Bit precision

from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig

tokenizer = AutoTokenizer.from_pretrained("yam-peleg/Hebrew-Gemma-11B-V2")
model = AutoModelForCausalLM.from_pretrained("yam-peleg/Hebrew-Gemma-11B-V2", quantization_config = BitsAndBytesConfig(load_in_4bit=True))

input_text = "שלום! מה שלומך היום?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))

📚 Documentation

Base Models

• 07.03.2024: Hebrew-Gemma-11B
• 16.03.2024: Hebrew-Gemma-11B-V2

Instruct Models

• 07.03.2024: Hebrew-Gemma-11B-Instruct

Model Details

Hebrew-Gemma-11B is an open - source LLM, a Hebrew/English pretrained generative text model with 11 billion parameters, based on the Gemma - 7B architecture from Google. It is a continued pretrain of gemma - 7b, extended to a larger scale and trained on 3B additional tokens of both English and Hebrew text data. The resulting model Gemma - 11B is a powerful general - purpose language model suitable for a wide range of natural language processing tasks, with a focus on Hebrew language understanding and generation.

Terms of Use

As an extension of Gemma - 7B, this model is subject to the original license and terms of use by Google. Gemma - 7B original Terms of Use: Terms

Notice

Hebrew-Gemma-11B-V2 is a pretrained base model and therefore does not have any moderation mechanisms.

📄 License

This model is under the gemma-terms-of-use.

👥 Authors

• Trained by Yam Peleg.
• In collaboration with Jonathan Rouach and Arjeo, inc.