💫 Community Model> Gemma 2 27b Instruct by Google

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord.

Model creator: Google
Original model: gemma-2-27b-it
GGUF quantization: provided by bartowski based on llama.cpp release b3259

Model Settings:

Requires LM Studio 0.2.27, update can be downloaded from here: https://lmstudio.ai

Model Summary:

Gemma 2 instruct is a a brand new model from Google in the Gemma family based on the technology from Gemini. Trained on a combination of web documents, code, and mathematics, this model should excel at anything you throw at it.
With 27B parameters, this fills in a really great gap between the typical ~8B and 70B models, and should be great for anyone with moderate VRAM availability.

Prompt Template:

Choose the 'Google Gemma Instruct' preset in your LM Studio.

Under the hood, the model will see a prompt that's formatted like so:

<start_of_turn>user
{prompt}<end_of_turn>
<start_of_turn>model

Note that this model does not support a System prompt.

Technical Details

Gemma 2 features the same extremely large vocabulary from release 1.1, which tends to help with multilingual and coding proficiency.

Gemma 2 27B was trained on a wide dataset of 13 trillion tokens, more than twice as many as Gemma 1.1, and an extra 60% over the 9B model, using similar datasets including:

  • Web Documents: A diverse collection of web text ensures the model is exposed to a broad range of linguistic styles, topics, and vocabulary. Primarily English-language content.
  • Code: Exposing the model to code helps it to learn the syntax and patterns of programming languages, which improves its ability to generate code or understand code-related questions.
  • Mathematics: Training on mathematical text helps the model learn logical reasoning, symbolic representation, and to address mathematical queries.

For more details check out their blog post here: https://huggingface.co/blog/gemma2

Special thanks

🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.

🙏 Special thanks to Kalomaze and Dampf for their work on the dataset (linked here) that was used for calculating the imatrix for all sizes.

Disclaimers

LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

Downloads last month
7,241
GGUF
Model size
27.2B params
Architecture
gemma2

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for lmstudio-community/gemma-2-27b-it-GGUF

Base model

google/gemma-2-27b
Quantized
(41)
this model