Instructions to use 2stacks/gemma3-12b-it-comedy-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Local Apps Settings
- Unsloth Studio
How to use 2stacks/gemma3-12b-it-comedy-v3 with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for 2stacks/gemma3-12b-it-comedy-v3 to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for 2stacks/gemma3-12b-it-comedy-v3 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for 2stacks/gemma3-12b-it-comedy-v3 to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="2stacks/gemma3-12b-it-comedy-v3", max_seq_length=2048, )
gemma3-12b-it-comedy-v3
QLoRA fine-tune of unsloth/gemma-3-12b-it on
2stacks/comedy-style-instruct
(316 examples: 120 verbatim H/A/J + 96 30-comedian variety + 100
in-the-style-of originals).
v3 scales up from the v2 4B base to test whether comedic logic (not just cadence) emerges with more model capacity. LoRA hyperparameters were backed off (r=32/α=64/4ep vs v2's r=64/α=128/6ep) to preserve base model capabilities — v2 over-fit and damaged arithmetic.
This model is trained to respond to user prompts with stand-up-style jokes, with a particular emphasis on the voices of Mitch Hedberg, Dave Attell, and Anthony Jeselnik. Style coverage extends to 30 additional comedians via the variety set.
Training
| Base | unsloth/gemma-3-12b-it |
| Method | QLoRA r=32, alpha=64, dropout 0 |
| Targets | q,k,v,o,gate,up,down |
| Schedule | 4 epochs, lr 0.0001, cosine, warmup 5 |
| Batch | 2×4 effective 8 |
| Seq len | 1024 |
| Hardware | 1×H100 on Modal |
| Final loss | 4.7038 |
W&B: gemma3-comedy-qlora / run gemma3-12b-it-r32-a64-4ep-316ex-v3.
Files
- LoRA adapter (peft format)
*.safetensors— merged 16-bit*.Q4_K_M.gguf— llama.cpp / Ollama format
Use
from transformers import AutoModelForCausalLM, AutoTokenizer
m = AutoModelForCausalLM.from_pretrained("2stacks/gemma3-12b-it-comedy-v3")
t = AutoTokenizer.from_pretrained("2stacks/gemma3-12b-it-comedy-v3")
Or in Ollama via the GGUF artifact.
Caveats
- Joke-by-default. This model trades general helpfulness for comedic voice. Use it for jokes; use the base model for tasks.
- Dark humor over-represented. Jeselnik / Attell / Stanhope material pushes the distribution toward edgier output. Expect the model to take dark turns even on innocent prompts.
- Non-commercial license. Per the underlying dataset, this model is CC-BY-NC-4.0 — research, education, and personal use only.
Attribution
The training data is sourced from publicly-available stand-up material released by 33 working comedians. Per-special and per-comedian attribution tables are maintained on the dataset card.
If you enjoy the voices this model imitates, please support those comedians by buying or streaming their specials directly.
- Downloads last month
- 79