Instructions to use mindchain/decider-4b-v2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use mindchain/decider-4b-v2-GGUF 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 mindchain/decider-4b-v2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mindchain/decider-4b-v2-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mindchain/decider-4b-v2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mindchain/decider-4b-v2-GGUF:Q4_K_M

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 mindchain/decider-4b-v2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mindchain/decider-4b-v2-GGUF:Q4_K_M

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 mindchain/decider-4b-v2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mindchain/decider-4b-v2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mindchain/decider-4b-v2-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mindchain/decider-4b-v2-GGUF with Ollama:
```
ollama run hf.co/mindchain/decider-4b-v2-GGUF:Q4_K_M
```
Unsloth Desktop

How to use mindchain/decider-4b-v2-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mindchain/decider-4b-v2-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mindchain/decider-4b-v2-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use mindchain/decider-4b-v2-GGUF with Docker Model Runner:
```
docker model run hf.co/mindchain/decider-4b-v2-GGUF:Q4_K_M
```

Lemonade

How to use mindchain/decider-4b-v2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mindchain/decider-4b-v2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.decider-4b-v2-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use mindchain/decider-4b-v2-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mindchain/decider-4b-v2-GGUF:Q4_K_M

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 mindchain/decider-4b-v2-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mindchain/decider-4b-v2-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mindchain/decider-4b-v2-GGUF:Q4_K_M

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 "mindchain/decider-4b-v2-GGUF:Q4_K_M" \
  --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"

mindchain commited on 21 days ago

Commit

2796fac

verified ·

1 Parent(s): 285bf89

Upload folder using huggingface_hub

Browse files

Files changed (4) hide show

.gitattributes +1 -0
README.md +66 -0
decider-4b.v2-Q4_K_M.gguf +3 -0
provenance.json +9 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+decider-4b.v2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

	@@ -0,0 +1,66 @@

+---
+license: apache-2.0
+base_model: Mapika/decider-4b
+base_model_revision: v2
+tags:
+- gguf
+- q4_k_m
+- decider
+- jev
+- system-one
+- decision-model
+- calibrated-decisions
+- semlf
+- qwen3.5
+- 4b
+- llama-cpp
+- quantized
+library_name: gguf
+pipeline_tag: text-classification
+language:
+- en
+- de
+---
+# decider-4b v2 — Q4_K_M GGUF (revision-pinned)
+**decider-4b at Hub tag `v2`** — exactly the revision that holds **JevBench v1.4.2 rank 1
+(Score 64.1 · Intel 49 · Calib 75 · Speed 93 · Cost 61)**, self-quantized with full
+provenance. Community GGUFs rarely pin which revision they quantized — this one does.
+## Which revision, and why it matters
+The upstream repo root is **v2.1**; `v2` lives under the `v2` tag. Per the upstream card,
+**v2 wins on hard decisions and is better calibrated there** (0.676 vs 0.649), while v2.1
+trades some of that for sampled play. For **logit-read typed decisions** (SemIf-style:
+state + lettered options → probabilities in one forward pass, no text generation) you
+want **v2**.
+| | |
+|---|---|
+| Source | [Mapika/decider-4b](https://huggingface.co/Mapika/decider-4b) @ tag `v2` (bf16, 8.4 GB) |
+| Quant | `Q4_K_M` via llama.cpp `convert_hf_to_gguf.py` (9575389) + `llama-quantize` |
+| Size / SHA256 | 2708804544 bytes / `f7e2e510ef51d212ea9b7fb8bf27906b5f516d7939ca847428fb91f6a8acfa79` |
+| Base | Qwen3.5-4B-Base (4.2B params, Apache-2.0) |
+| Quantized by | mindchain (JEV stack), Kaggle CPU, pipeline in `provenance.json` |
+## Usage — System-One decisions from logits (no generation)
+```bash
+llama-server -m decider-4b.v2-Q4_K_M.gguf -ngl 99 -c 2048 --port 8080
+```
+Send the SemIf minimal prompt (state + criteria + lettered options) and read the
+option-letter probabilities straight from the logits — one forward pass, no decoding
+loop. Apply the per-answer-type temperature from the upstream card for calibrated
+confidences. Works with any llama.cpp runtime (server, Termux/Android, ChatterUI).
+## Honest benchmark note (protocol separation)
+JevBench v1.4.2 ranks decider-4b v2 #1 (64.1). On the independent JEV-stack gold set, a
+decider-4b Q4 measured **0.5975 accuracy vs 0.7635 for a fine-tuned encoder-decider
+(laya)** — different protocols crown different winners. Measure on YOUR domain before
+shipping.
+- Benchmark: [JevBench v1.4.2](https://benchmarkheaven.com/jev-models)
+- JEV decision-model stack: calibration-first System-One models, gold-set gated deployments

decider-4b.v2-Q4_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f7e2e510ef51d212ea9b7fb8bf27906b5f516d7939ca847428fb91f6a8acfa79
+size 2708804544

provenance.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+  "source_repo": "Mapika/decider-4b",
+  "source_revision": "v2",
+  "file": "decider-4b.v2-Q4_K_M.gguf",
+  "bytes": 2708804544,
+  "sha256": "f7e2e510ef51d212ea9b7fb8bf27906b5f516d7939ca847428fb91f6a8acfa79",
+  "quant": "Q4_K_M",
+  "converted_with": "llama.cpp convert_hf_to_gguf.py @ commit 9575389, --no-mtp, bf16->Q4_K_M"
+}