Instructions to use star-ga/mind-mem-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use star-ga/mind-mem-4b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="star-ga/mind-mem-4b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("star-ga/mind-mem-4b")
model = AutoModelForCausalLM.from_pretrained("star-ga/mind-mem-4b", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use star-ga/mind-mem-4b 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 star-ga/mind-mem-4b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf star-ga/mind-mem-4b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf star-ga/mind-mem-4b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf star-ga/mind-mem-4b: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 star-ga/mind-mem-4b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf star-ga/mind-mem-4b: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 star-ga/mind-mem-4b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf star-ga/mind-mem-4b:Q4_K_M

Use Docker

docker model run hf.co/star-ga/mind-mem-4b:Q4_K_M

LM Studio
Jan

vLLM

How to use star-ga/mind-mem-4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "star-ga/mind-mem-4b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "star-ga/mind-mem-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/star-ga/mind-mem-4b:Q4_K_M

SGLang

How to use star-ga/mind-mem-4b with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "star-ga/mind-mem-4b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "star-ga/mind-mem-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "star-ga/mind-mem-4b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "star-ga/mind-mem-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use star-ga/mind-mem-4b with Ollama:
```
ollama run hf.co/star-ga/mind-mem-4b:Q4_K_M
```
Unsloth Desktop

How to use star-ga/mind-mem-4b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf star-ga/mind-mem-4b: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": "star-ga/mind-mem-4b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use star-ga/mind-mem-4b with Docker Model Runner:
```
docker model run hf.co/star-ga/mind-mem-4b:Q4_K_M
```

Lemonade

How to use star-ga/mind-mem-4b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull star-ga/mind-mem-4b:Q4_K_M

Run and chat with the model

lemonade run user.mind-mem-4b-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use star-ga/mind-mem-4b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf star-ga/mind-mem-4b: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 star-ga/mind-mem-4b:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use star-ga/mind-mem-4b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf star-ga/mind-mem-4b: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 "star-ga/mind-mem-4b: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"

star-ga commited on May 5

Commit

e2a77aa

verified ·

1 Parent(s): 6815037

docs: card fixes — full-FT (was QLoRA), library_name=transformers, drop qlora tag

Browse files

Files changed (1) hide show

README.md +12 -12

README.md CHANGED Viewed

@@ -2,13 +2,13 @@
 language:
   - en
 license: apache-2.0
-library_name: peft
 tags:
   - mind-mem
   - memory
   - governance
   - retrieval-augmented
-  - qlora
   - qwen3.5
   - text-generation
   - conversational
@@ -20,7 +20,7 @@ pipeline_tag: text-generation
 A governance-aware memory-assistant model for [mind-mem](https://github.com/star-ga/mind-mem) — an auditable, contradiction-safe memory layer for coding agents (MCP-compatible).
-This checkpoint is a **QLoRA fine-tune** of `Qwen/Qwen3.5-4B`, trained on the mind-mem v3.9.0 source tree: all **81 MCP tool signatures** (24 new in the v3.4 → v3.9 surface — incl. `compile_truth_walkthrough`, `recall_with_persona`, `pipeline_status`, `reindex_dirty`, MIC/MAP wire format, governance hooks, kernels), block-type schemas (with the new `TransformHash` field, v3.9), full CHANGELOG history through v3.9.0, the docs/ tree, and curated end-to-end governance workflow transcripts.
 ## What's new in v3.9 vs. v3.0
@@ -49,18 +49,15 @@ The v3.0 fine-tune did not know about any of these surfaces; this revision resto
 ## Usage
-### Load the adapter (bf16 base + LoRA)
 ```python
-from peft import PeftModel
 from transformers import AutoModelForCausalLM, AutoTokenizer
-BASE = "Qwen/Qwen3.5-4B"
-ADAPTER = "star-ga/mind-mem-4b"
-tokenizer = AutoTokenizer.from_pretrained(BASE)
-base = AutoModelForCausalLM.from_pretrained(BASE, torch_dtype="bfloat16", device_map="auto")
-model = PeftModel.from_pretrained(base, ADAPTER)
 messages = [
     {"role": "system", "content": "You are mind-mem-4b, a memory-governance assistant."},
@@ -83,10 +80,13 @@ llama-cli -m ./gguf/mind-mem-4b-Q4_K_M.gguf -p "Show me a TransformHash block te
 ### Pin a prior revision
-The v3.0 fine-tune is preserved as a HF revision tag:
 ```python
-PeftModel.from_pretrained(base, "star-ga/mind-mem-4b", revision="v3.0.0")
 ```
 ## Training recipe

 language:
   - en
 license: apache-2.0
+library_name: transformers
 tags:
   - mind-mem
   - memory
   - governance
   - retrieval-augmented
+  - full-fine-tune
   - qwen3.5
   - text-generation
   - conversational
 A governance-aware memory-assistant model for [mind-mem](https://github.com/star-ga/mind-mem) — an auditable, contradiction-safe memory layer for coding agents (MCP-compatible).
+This checkpoint is a **full fine-tune** of `Qwen/Qwen3.5-4B` (every one of the ~4 B parameters trained), trained on the mind-mem v3.9.0 source tree: all **81 MCP tool signatures** (24 new in the v3.4 → v3.9 surface — incl. `compile_truth_walkthrough`, `recall_with_persona`, `pipeline_status`, `reindex_dirty`, MIC/MAP wire format, governance hooks, kernels), block-type schemas (with the new `TransformHash` field, v3.9), full CHANGELOG history through v3.9.0, the docs/ tree, and curated end-to-end governance workflow transcripts.
 ## What's new in v3.9 vs. v3.0
 ## Usage
+### Load the model (bf16 full fine-tune)
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
+REPO = "star-ga/mind-mem-4b"
+tokenizer = AutoTokenizer.from_pretrained(REPO)
+model = AutoModelForCausalLM.from_pretrained(REPO, dtype="bfloat16", device_map="auto")
 messages = [
     {"role": "system", "content": "You are mind-mem-4b, a memory-governance assistant."},
 ### Pin a prior revision
+The v3.0 QLoRA fine-tune is preserved as a HF revision tag:
 ```python
+from peft import PeftModel
+from transformers import AutoModelForCausalLM
+base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B", dtype="bfloat16", device_map="auto")
+model = PeftModel.from_pretrained(base, "star-ga/mind-mem-4b", revision="v3.0.0")
 ```
 ## Training recipe