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:

general purpose

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 -y

Once, setup you can proceed to run the model by running the snippet below:

from transformers import pipeline
import torch
model_id = "EpistemeAI/metatune-gpt20b-R1.1"
pipe = pipeline(
    "text-generation",
    model=model_id,
    torch_dtype="auto",
    device_map="auto",
)
messages = [
    {"role": "user", "content": "Derive the Euler–Lagrange equation from the principle of stationary action.""},
]
outputs = pipe(
    messages,
    max_new_tokens=3000,
)
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.

Risk:

Prompt safely with recursive self improvement model. Use safety gpt oss 20b for model safety analysis
Do not use this model for creating nuclear, biological and chemical weapons.

Benchmark

Code to duplicate the benchmark (Using +std for final result)

#gpqa diamond
!lm_eval --model hf --model_args pretrained=EpistemeAI/metatune-gpt20b-R1.1,parallelize=True,dtype=bfloat16 --tasks gpqa_diamond_cot_zeroshot  --num_fewshot 0 --gen_kwargs temperature=0.9,top_p=0.9,max_new_tokens=2048 --batch_size auto:4 --limit 10  --device cuda:0 --output_path ./eval_harness/gpt-oss-20b3
#gsm8k cot
!lm_eval --model hf --model_args pretrained=EpistemeAI/metatune-gpt20b-R1.1,parallelize=True,dtype=bfloat16 --tasks gsm8k_cot_llama  --num_fewshot 0 --gen_kwargs temperature=0.9,top_p=0.9,max_new_tokens=2048 --batch_size auto:4 --limit 10  --device cuda:0 --output_path ./eval_harness/gpt-oss-20b3

hf (pretrained=EpistemeAI/metatune-gpt20b-R1.1,parallelize=True,dtype=bfloat16), gen_kwargs: (temperature=0.9,top_p=0.9,max_new_tokens=2048), limit: 10.0, num_fewshot: 0, batch_size: auto:4