Instructions to use adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF",
	filename="gpt_oss_20b_11082025_hesoyam-f16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF:F16

Use Docker

docker model run hf.co/adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF:F16

LM Studio
Jan
Ollama
How to use adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF with Ollama:
```
ollama run hf.co/adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF:F16
```

Unsloth Studio

How to use adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF 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 adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF 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 adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF to start chatting

Docker Model Runner
How to use adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF with Docker Model Runner:
```
docker model run hf.co/adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF:F16
```

Lemonade

How to use adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF:F16

Run and chat with the model

lemonade run user.GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF-F16

List all available models

lemonade list

GPT-OSS-20B fine-tuned on adamo1139/HESOYAM_v0.4 dataset, 1 epoch, chatml format that erases reasoning. 1024 rank, 128 alpha QLoRA made with Unsloth. It will be undergoing further preference alignment once some issues preventing me from doing it right now will be patched out.

Total batch size 16, learning rate 0.0002 with cosine schedule, with sample packing enabled. Training took about 8 hours on single 3090 Ti.

Loss curve looks a bit underwhelming.

I tried merging this lora with the huizimao/gpt-oss-20b-uncensored-mxfp4 but that wasn't producing great effects.

No reasoning is present, and model definitely learns something from the dataset, but it feels pretty dumb, so it could be a wrong path.

Downloads last month: 60

GGUF

Model size

21B params

Architecture

gpt-oss

Hardware compatibility

4-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF

Base model

openai/gpt-oss-20b

Quantized

(201)

this model

adamo1139
/

GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF

Model tree for adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF

Dataset used to train adamo1139/GPT-OSS-20B-HESOYAM-1108-WIP-CHATML-GGUF