Downloads · 30 days
50
17% of all-time downloads
gemma3-4b-it-comedy-v2
2stacks/gemma3-4b-it-comedy-v2
gemma3-4b-it-comedy-v2 is a machine learning model from 2stacks. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as cc-by-nc-4.0.
QLoRA fine-tune of unsloth/gemma-3-4b-it on 2stacks/comedy-style-instruct (316 examples: 120 verbatim H/A/J + 96 30-comedian variety + 100 in-the-style-of originals).
All-time downloads
299
Public
Parameters
4.3B
11.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors9.1 GB · 78%
At a glance
- License
- cc-by-nc-4.0
- Model type
- gemma3
- Access
- Public
- Created
- May 10, 2026
- Updated
- May 10, 2026
- SHA
- 65ece204
Base models
Datasets
Model card
From the Hugging Face model README
gemma3-4b-it-comedy-v2
QLoRA fine-tune of unsloth/gemma-3-4b-it on
2stacks/comedy-style-instruct
(316 examples: 120 verbatim H/A/J + 96 30-comedian variety + 100
in-the-style-of originals).
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-3-4b-it |
| Method | QLoRA r=64, alpha=128, dropout 0 |
| Targets | q,k,v,o,gate,up,down |
| Schedule | 6 epochs, lr 0.0001, cosine, warmup 5 |
| Batch | 2×4 effective 8 |
| Seq len | 1024 |
| Hardware | 1×H100 on Modal |
| Final loss | 3.8498 |
W&B: gemma3-comedy-qlora / run gemma3-4b-it-r64-a128-6ep-316ex-v2.
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/gemma3-4b-it-comedy-v2")
t = AutoTokenizer.from_pretrained("2stacks/gemma3-4b-it-comedy-v2")
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.
- Type
- gemma3
- License
- cc-by-nc-4.0
- Languages
- en
- Created
- May 10, 2026
- Updated
- May 10, 2026