Instructions to use csoai/sov34-1p5b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use csoai/sov34-1p5b 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 csoai/sov34-1p5b:F16
# Run inference directly in the terminal:
llama cli -hf csoai/sov34-1p5b:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf csoai/sov34-1p5b:F16
# Run inference directly in the terminal:
llama cli -hf csoai/sov34-1p5b: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 csoai/sov34-1p5b:F16
# Run inference directly in the terminal:
./llama-cli -hf csoai/sov34-1p5b: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 csoai/sov34-1p5b:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf csoai/sov34-1p5b:F16

Use Docker

docker model run hf.co/csoai/sov34-1p5b:F16

LM Studio
Jan
Ollama
How to use csoai/sov34-1p5b with Ollama:
```
ollama run hf.co/csoai/sov34-1p5b:F16
```

Unsloth Studio

How to use csoai/sov34-1p5b 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 csoai/sov34-1p5b 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 csoai/sov34-1p5b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for csoai/sov34-1p5b to start chatting

How to use csoai/sov34-1p5b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf csoai/sov34-1p5b:F16

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": "csoai/sov34-1p5b:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use csoai/sov34-1p5b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf csoai/sov34-1p5b:F16

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 csoai/sov34-1p5b:F16

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use csoai/sov34-1p5b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf csoai/sov34-1p5b:F16

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 "csoai/sov34-1p5b:F16" \
  --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 csoai/sov34-1p5b with Docker Model Runner:
```
docker model run hf.co/csoai/sov34-1p5b:F16
```

Lemonade

How to use csoai/sov34-1p5b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull csoai/sov34-1p5b:F16

Run and chat with the model

lemonade run user.sov34-1p5b-F16

List all available models

lemonade list

sov34-1.5b — EXPERIMENTAL (dual-gate candidate: FAILED gate 2, published with failures included)

Register: measurement/attestation only. This model makes no capability claims. Read the numbers before use.

LoRA (r16) on Qwen2.5-1.5B, trained on 4,853 governance-corpus rows (eval_loss 0.821). This was a candidate successor to sov33-unified under a dual-gate rule: beat it on generality AND on the frozen governance split, or make no claims. Gate 2 failed. We publish the data anyway — failures included is the point of the measurement platform.

Measured gates (identical 170 held-out items, frozen split v1, set-F1)

Model	set-F1	CI95 (BCa n=2000)
sov33-unified	0.2508	[0.221, 0.283]
sov34 (this model)	0.1975	[0.169, 0.226]
base qwen2.5-1.5b	0.1767	[0.151, 0.205]

Generality (lm-eval arc_easy, validated hf lane): sov34 0.7504 ± 0.0089; base 0.7551 ± 0.0088 (preserved within noise). sov33-unified for contrast: 0.2534 (near-random — disclosed specialist profile).

Verdict

Gate 1 (generality): PASS. Gate 2 (governance frozen split): FAIL vs 0.2508. Dual-gate NOT MET. The LoRA nudged governance retrieval above its own base but does not match the specialist. Consistent with the published canon: closed-book small models cannot hold statutory citation — retrieval grounding is required, not optional.

What this model is for

Experimentation, reproduction, router-substrate research (a 1.5B that keeps generality while carrying governance signal). NOT for compliance decisions, NOT a certified anything.

Reproduce

Harness + results: HF dataset csoai/aiact-frozen-split-harness (incl. sov34_dualgate_triangulation_2026-08-03.json). Triangulation: sov33-unified / sov34 / base on byte-identical item sets.

Lane warning

All numbers measured via validated lanes only (lm_eval --model hf; direct ollama /api/generate; OpenRouter API). The llama.cpp llama-server + lm_eval local-completions lane was invalidated 2026-08-03 (instrument fault; see csoai/lmeval-official-format INVALIDATED.md).

Downloads last month: -

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

16-bit

Inference Providers NEW

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

csoai
/

sov34-1p5b

sov34-1.5b — EXPERIMENTAL (dual-gate candidate: FAILED gate 2, published with failures included)

Measured gates (identical 170 held-out items, frozen split v1, set-F1)

Verdict

What this model is for

Reproduce

Lane warning

Dataset used to train csoai/sov34-1p5b