geminigooner's picture
|
download
raw
10.9 kB
metadata
base_model: p-e-w/gemma-4-E2B-it-heretic-ara
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - gemma4
  - roleplay
  - uncensored
  - multimodal
  - vision
  - audio
license: other
license_name: firefly-v4-attribution
license_link: LICENSE
language:
  - en
๐Ÿ”ฅ

Firefly-v4

Uncensored multimodal roleplay model with switchable reasoning โ€” sees, hears, and creates without limits.

text-generation vision audio unsloth gemma4

What is Firefly-v4

Firefly-v4 is an uncensored, multimodal roleplay and creative writing model fine-tuned from gemma-4-E2B-it-heretic-ara using Unsloth. It inherits Gemma 4's native vision and audio capabilities โ€” it can see images and process audio as part of a conversation, not as a bolted-on pipeline.

Built for immersive, unfiltered RP and storytelling. No refusals, no moralizing, no character breaks. Works equally well for general creative tasks and instruction following.

๐Ÿ”“
Uncensored

No refusals or alignment guardrails. Full creative freedom for any scenario.

๐Ÿ‘๏ธ
Vision

Natively understands images โ€” describe scenes, react to photos, analyze reference art mid-RP.

๐ŸŽง
Audio

Processes audio input natively via Gemma 4's multimodal architecture.

๐Ÿง 
Switchable Reasoning

Toggle chain-of-thought on or off with a single tag โ€” you control the depth.

๐Ÿง  Reasoning Toggle

Prefix your system prompt with <|think|> and the model thinks before it speaks. Leave it out and it responds directly.

โšก THINKING ON
<|think|>You are in a roleplay as a Furry named Blaze.

Better coherence for complex scenes.

โ—‹ THINKING OFF
You are in a roleplay as a Furry named Blaze.

Faster, more spontaneous output.

Training

base_model p-e-w/gemma-4-E2B-it-heretic-ara
method Fine-tuned with Unsloth
modalities Text + Vision + Audio (native Gemma 4)
focus Uncensored roleplay, creative writing, hybrid reasoning

๐Ÿ“œ License

Firefly-v4 Attribution License

1. Free for personal and non-commercial use. You may use, modify, merge, and distribute this model freely for any personal, educational, or non-commercial purpose.
2. Commercial use requires attribution. Any commercial product, service, API, or offering that uses this model โ€” or any derivative, merge, or quantization of it โ€” must prominently include the following attribution:
Based on Guilherme34/Firefly-v4

Must include the model name (Firefly-v4) and author (Guilherme34), linking to the original HuggingFace repo when possible.

3. Derivatives inherit this license. Any fine-tune, merge, distillation, or quantization must carry forward the same attribution terms.
4. No implied endorsement. Attribution does not imply endorsement by the original author.
5. No warranty. Provided "as-is" without warranty. The author is not liable for any damages arising from use.
โš ๏ธ Disclaimer

This model is uncensored and will generate content without built-in refusals. It is intended for creative fiction and roleplay between consenting adults. The creator is not responsible for how the model is used. Do not use it to produce content that is illegal in your jurisdiction.

Made with ๐Ÿ”ฅ by Guilherme34

Xet Storage Details

Size:
10.9 kB
ยท
Xet hash:
d4379c3a8874b312727ecf4687fefe1e9da8bf4a41fc6dfd651dc1fe25510f6c

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.