Instructions to use Myric/gpt-oss-78B-pruned-experiment with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Myric/gpt-oss-78B-pruned-experiment with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Myric/gpt-oss-78B-pruned-experiment
# Run inference directly in the terminal:
llama cli -hf Myric/gpt-oss-78B-pruned-experiment

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Myric/gpt-oss-78B-pruned-experiment
# Run inference directly in the terminal:
llama cli -hf Myric/gpt-oss-78B-pruned-experiment

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 Myric/gpt-oss-78B-pruned-experiment
# Run inference directly in the terminal:
./llama-cli -hf Myric/gpt-oss-78B-pruned-experiment

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 Myric/gpt-oss-78B-pruned-experiment
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Myric/gpt-oss-78B-pruned-experiment

Use Docker

docker model run hf.co/Myric/gpt-oss-78B-pruned-experiment

LM Studio
Jan

vLLM

How to use Myric/gpt-oss-78B-pruned-experiment with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Myric/gpt-oss-78B-pruned-experiment"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Myric/gpt-oss-78B-pruned-experiment",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Myric/gpt-oss-78B-pruned-experiment

Ollama
How to use Myric/gpt-oss-78B-pruned-experiment with Ollama:
```
ollama run hf.co/Myric/gpt-oss-78B-pruned-experiment
```

Unsloth Studio

How to use Myric/gpt-oss-78B-pruned-experiment 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 Myric/gpt-oss-78B-pruned-experiment 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 Myric/gpt-oss-78B-pruned-experiment to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Myric/gpt-oss-78B-pruned-experiment to start chatting

How to use Myric/gpt-oss-78B-pruned-experiment with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Myric/gpt-oss-78B-pruned-experiment

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Myric/gpt-oss-78B-pruned-experiment"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use Myric/gpt-oss-78B-pruned-experiment with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Myric/gpt-oss-78B-pruned-experiment

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Myric/gpt-oss-78B-pruned-experiment" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use Myric/gpt-oss-78B-pruned-experiment with Docker Model Runner:
```
docker model run hf.co/Myric/gpt-oss-78B-pruned-experiment
```

Lemonade

How to use Myric/gpt-oss-78B-pruned-experiment with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Myric/gpt-oss-78B-pruned-experiment

Run and chat with the model

lemonade run user.gpt-oss-78B-pruned-experiment-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use Myric/gpt-oss-78B-pruned-experiment with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Myric/gpt-oss-78B-pruned-experiment

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Myric/gpt-oss-78B-pruned-experiment

Run Hermes

hermes

Atomic Chat

Myric commited on 6 days ago

Commit

2b865a7

verified ·

1 Parent(s): eca8dbb

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -76,7 +76,7 @@ All numbers below are real `llama-perplexity`/`llama-server` runs, validated on
 independent llama.cpp implementations** (mainline `ggml-org/llama.cpp` and a
 Puzzle-support fork) agreeing to within ~1%, same corpus, same settings throughout.
-| | original 120b | **pruned "85B"** | native 20b (for reference) |
 |---|---:|---:|---:|
 | total params | 116.8B | **78.3B** | 20.9B |
 | layers × experts/layer | 36 × 128 | 36 × 85 | 24 × 32 |
@@ -139,7 +139,7 @@ MXFP4 calibration already achieved, with no guaranteed improvement.
 ## Files
-- `gpt-oss-85B-pruned.gguf` — the pruned checkpoint, converted via mainline
   `llama.cpp`, MXFP4-native experts preserved (not dequantized), bf16 for
   attention/router/norms — same mixed-precision layout as the original release.
 - `kept_expert_indices.json` — the exact per-layer set of retained expert indices

 independent llama.cpp implementations** (mainline `ggml-org/llama.cpp` and a
 Puzzle-support fork) agreeing to within ~1%, same corpus, same settings throughout.
+| | original 120b | **pruned 78B** | native 20b (for reference) |
 |---|---:|---:|---:|
 | total params | 116.8B | **78.3B** | 20.9B |
 | layers × experts/layer | 36 × 128 | 36 × 85 | 24 × 32 |
 ## Files
+- `gpt-oss-78B-pruned.gguf` — the pruned checkpoint, converted via mainline
   `llama.cpp`, MXFP4-native experts preserved (not dequantized), bf16 for
   attention/router/norms — same mixed-precision layout as the original release.
 - `kept_expert_indices.json` — the exact per-layer set of retained expert indices