Raze V3-hybrid

This is a custom QLoRA fine-tune of the Gemma-3n-E4B-it model.

Model Purpose

This model is primarily intended to act as a conversational, silly friend rather than a helper, assistant, etc.

  • Personality: It has a distinct personality, significantly different from previous iterations (v1 and v2).
  • Fun Feature: You can meow at it, and it will meow back!
  • Knowledge: While it retains the base knowledge of Gemma, this information may be obscured or incorrect due to the fine-tuning process. Never treat its outputs as factual.

Training Details

This model (v3) was trained using a combination of personal and secondary data sources.

Category Description
Data Source 1 Online conversations from the developer's friend group (used with consent).
Data Source 2 A second, large dataset compiled from a myriad of sources.
Comparison This model is significantly more legible and effective than v1 and v2, though it exhibits a different personality. (A related, more stable counterpart, v3-calcium, was unfortunately lost.)

Prompt Formatting

The training data utilized two primary formatting structures to allow the model to handle both single-user and group conversations effectively. Using these formats will yield the most accurate personality response (though you can omit the "roleplay as" part):

1. Group Conversation Style (50% of Data)

{"messages": [{"role": "user", "content": "Below is a chat log. Continue the conversation as [username1]. \n\n[username1]: [message1]\n[username2]:[message2]\n\n"}, {"role": "assistant", "content": "[response message]"}]}

2. One-on-One Roleplay Style (50% of Data)

{"messages": [{"role": "user", "content": "Roleplay as [username]. Reply to the following message.\n\n[message]\n\n"}, {"role": "assistant", "content": "[response]"}]}

Caveats and Limitations

⚠️ Warning: Instability

This model is unstable. Many outputs may only be partially in-context or incoherent. Use with caution.

Technical Limitations

  • Visual Capabilities: This model does not retain the visual capabilities of the base Gemma model.
  • Available Files: This repository only contains GGUF files. Safetensors files were removed.

Note on Development

This was a minor personal project done for fun and was developed with assistance from Gemini-3-preview.

translation: I DON'T KNOW HOW THIS WORKS AT ALL

License and Terms

This model is a derivative of Gemma 3n E4B by Google.

Safety Disclaimer: This model was not explicitly trained to generate harmful content or violate the Gemma Prohibited Use Policy (PUP). Content that violates the PUP may still be generated randomly.

Gemma is provided under and subject to the Gemma Terms of Use found at https://ai.google.dev/gemma/terms.

By using this model, you agree to the Gemma Terms of Use and the Prohibited Use Policy. (https://ai.google.dev/gemma/prohibited_use_policy)

Downloads last month
527
GGUF
Model size
7B params
Architecture
gemma3n
Hardware compatibility
Log In to view the estimation

We're not able to determine the quantization variants.

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for 4cee/raze-v3-hybrid-gemma3n-e4b

Quantized
(55)
this model