Model Card
We release open-weight metatune-gpt20b, fine tuned version of OpenAI's gpt-oss-20b model, this is one of the first public release recursive self improving AI.
Generates new data for itself,
Evaluates its performance, and
Adjusts its own hyperparameters based on improvement metrics.
Use cases:
genuinely demonstrate scientific and mathematical understanding at a postdoctoral level.
coding
Topics: Euler–Lagrange equation, vector calculus, statistical mechanics
additinal information
Due to recursive self improvement method, there is no final model, but improved model, this is a 5th metacycle(generation) improved checkpoint model.
Guardrails:
generally, please set reasoning = "high", it will usually prevent jailbreaking and prompt injection
use safety gpt oss 20b for guardrails before this model: openai/gpt-oss-safeguard-20b
Inference examples
Transformers
You can use
gpt-oss-120b and
gpt-oss-20b with Transformers. If you use the Transformers chat template, it will automatically apply the
harmony response format . If you use
model.generate directly, you need to apply the harmony format manually using the chat template or use our
openai-harmony package.
To get started, install the necessary dependencies to setup your environment:
pip install -U transformers kernels torch For Google Colab (free/Pro)
!pip install -q --upgrade torch
!pip install -q transformers triton==3.4 kernels
!pip uninstall -q torchvision torchaudio -yOnce, setup you can proceed to run the model by running the snippet below:
1 from transformers import pipeline
2 import torch
3 model_id = "EpistemeAI/metatune-gpt20b-R1"
4 pipe = pipeline (
5 "text-generation" ,
6 model = model_id ,
7 torch_dtype = "auto" ,
8 device_map = "auto" ,
9 )
10 messages = [
11 { "role" : "user" , "content" : "Derive the Euler–Lagrange equation from the principle of stationary action." " } ,
12 ]
13 outputs = pipe (
14 messages ,
15 max_new_tokens = 3000 ,
16 )
17 print ( outputs [ 0 ] [ "generated_text" ] [ - 1 ] )
Reasoning levels
You can adjust the reasoning level that suits your task across three levels:
Low: Fast responses for general dialogue.Medium: Balanced speed and detail.High: Deep and detailed analysis.
The reasoning level can be set in the system prompts, e.g., "Reasoning: high".
Tool use
The gpt-oss models are excellent for:
Web browsing (using built-in browsing tools)
Function calling with defined schemas
Agentic operations like browser tasks
Fine-tuning
Both gpt-oss models can be fine-tuned for a variety of specialized use cases.
This smaller model
gpt-oss-20b can be fine-tuned on consumer hardware, whereas the larger
gpt-oss-120b can be fine-tuned on a single H100 node.
Benchmark
Tasks metatune R0 metatune R1 Llama 4 Maverick gsm8k_cot 0.91 0.9796 - gpqa_diamond_cot_n_shot 0.722 - hellaswag 0.421 0.525 - arc_challenge 0.349 0.349 - winogrande 0.7851 0.5928 -
Inspiration:
Jurgen Schmidhuber
Uploaded finetuned model
Developed by: EpistemeAILicense: apache-2.0Finetuned from model : unsloth/gpt-oss-20b-unsloth-bnb-4bit
This gpt_oss model was trained 2x faster with
Unsloth and Huggingface's TRL library.
