Instructions to use bartowski/UserRepGen-4B-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 bartowski/UserRepGen-4B-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 bartowski/UserRepGen-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/UserRepGen-4B-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 bartowski/UserRepGen-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/UserRepGen-4B-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 bartowski/UserRepGen-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bartowski/UserRepGen-4B-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 bartowski/UserRepGen-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bartowski/UserRepGen-4B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/bartowski/UserRepGen-4B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use bartowski/UserRepGen-4B-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/bartowski/UserRepGen-4B-GGUF:Q4_K_M

Ollama
How to use bartowski/UserRepGen-4B-GGUF with Ollama:
```
ollama run hf.co/bartowski/UserRepGen-4B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use bartowski/UserRepGen-4B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bartowski/UserRepGen-4B-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": "bartowski/UserRepGen-4B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use bartowski/UserRepGen-4B-GGUF with Docker Model Runner:
```
docker model run hf.co/bartowski/UserRepGen-4B-GGUF:Q4_K_M
```

Lemonade

How to use bartowski/UserRepGen-4B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bartowski/UserRepGen-4B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.UserRepGen-4B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use bartowski/UserRepGen-4B-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 bartowski/UserRepGen-4B-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 bartowski/UserRepGen-4B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use bartowski/UserRepGen-4B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bartowski/UserRepGen-4B-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 "bartowski/UserRepGen-4B-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"

UserRepGen-4B-GGUF / layouts /UserRepGen-4B-IQ2_M.layout.json

bartowski

Upload folder using huggingface_hub

6fcca44 verified 4 days ago

Raw History Blame Contribute Delete

7.38 kB

	{
	"model": "/media/m2teamgroup/models/UserRepGen-4B-GGUF/UserRepGen-4B-bf16.gguf",
	"imatrix": "/media/m2teamgroup/models/UserRepGen-4B-GGUF/UserRepGen-4B-imatrix.gguf",
	"ftype": "IQ2_M",
	"base_type": "iq2_s",
	"family": "iq",
	"recipe": "ident",
	"variant": "shr0.70",
	"auto_crush": false,
	"rung_mode": "share",
	"tier": "M",
	"rung_share": 0.7,
	"crush_pass_bytes": null,
	"embd_shares": {
	"token_embd.weight": {
	"share": 0.2408,
	"type": "q3_k"
	}
	},
	"arch": "hybrid",
	"tied": true,
	"n_layer": 32,
	"body_rule": true,
	"pins": {
	"^blk\\.0\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.0\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.1\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.1\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.2\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.2\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.4\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.4\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.5\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.5\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.6\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.6\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.8\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.8\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.9\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.9\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.10\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.10\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.12\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.12\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.13\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.13\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.14\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.14\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.16\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.16\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.17\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.17\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.18\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.18\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.20\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.20\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.21\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.21\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.22\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.22\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.24\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.24\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.25\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.25\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.26\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.26\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.28\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.28\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.29\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.29\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.30\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32",
	"^blk\\.30\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32"
	},
	"shape_pins": {},
	"fixed_pins": {
	"blk.0.ssm_alpha.weight": "f32",
	"blk.0.ssm_beta.weight": "f32",
	"blk.1.ssm_alpha.weight": "f32",
	"blk.1.ssm_beta.weight": "f32",
	"blk.2.ssm_alpha.weight": "f32",
	"blk.2.ssm_beta.weight": "f32",
	"blk.4.ssm_alpha.weight": "f32",
	"blk.4.ssm_beta.weight": "f32",
	"blk.5.ssm_alpha.weight": "f32",
	"blk.5.ssm_beta.weight": "f32",
	"blk.6.ssm_alpha.weight": "f32",
	"blk.6.ssm_beta.weight": "f32",
	"blk.8.ssm_alpha.weight": "f32",
	"blk.8.ssm_beta.weight": "f32",
	"blk.9.ssm_alpha.weight": "f32",
	"blk.9.ssm_beta.weight": "f32",
	"blk.10.ssm_alpha.weight": "f32",
	"blk.10.ssm_beta.weight": "f32",
	"blk.12.ssm_alpha.weight": "f32",
	"blk.12.ssm_beta.weight": "f32",
	"blk.13.ssm_alpha.weight": "f32",
	"blk.13.ssm_beta.weight": "f32",
	"blk.14.ssm_alpha.weight": "f32",
	"blk.14.ssm_beta.weight": "f32",
	"blk.16.ssm_alpha.weight": "f32",
	"blk.16.ssm_beta.weight": "f32",
	"blk.17.ssm_alpha.weight": "f32",
	"blk.17.ssm_beta.weight": "f32",
	"blk.18.ssm_alpha.weight": "f32",
	"blk.18.ssm_beta.weight": "f32",
	"blk.20.ssm_alpha.weight": "f32",
	"blk.20.ssm_beta.weight": "f32",
	"blk.21.ssm_alpha.weight": "f32",
	"blk.21.ssm_beta.weight": "f32",
	"blk.22.ssm_alpha.weight": "f32",
	"blk.22.ssm_beta.weight": "f32",
	"blk.24.ssm_alpha.weight": "f32",
	"blk.24.ssm_beta.weight": "f32",
	"blk.25.ssm_alpha.weight": "f32",
	"blk.25.ssm_beta.weight": "f32",
	"blk.26.ssm_alpha.weight": "f32",
	"blk.26.ssm_beta.weight": "f32",
	"blk.28.ssm_alpha.weight": "f32",
	"blk.28.ssm_beta.weight": "f32",
	"blk.29.ssm_alpha.weight": "f32",
	"blk.29.ssm_beta.weight": "f32",
	"blk.30.ssm_alpha.weight": "f32",
	"blk.30.ssm_beta.weight": "f32"
	},
	"embeddings": {
	"token_embd.weight": "q3_k"
	},
	"bytes": {
	"heuristic_body+embd": 1795031040,
	"map_body+embd": 1555445760,
	"ratio": 0.8665,
	"note": "quantizable, unpinned tensors only; pinned/unquantized tensors are identical in both"
	},
	"body_base_share": 0.7,
	"body_bpw": 2.877,
	"body_bpw_heuristic": 3.047,
	"total_params": 4205751296,
	"file_bytes_pred": 1575020544,
	"file_bpw_pred": 2.996,
	"histogram": {
	"attn_gate": {
	"iq2_s": 23,
	"q5_k": 1
	},
	"attn_k": {
	"iq4_xs": 4,
	"q4_k": 4
	},
	"attn_output": {
	"iq4_xs": 7,
	"q5_k": 1
	},
	"attn_q": {
	"iq2_s": 8
	},
	"attn_qkv": {
	"iq2_s": 23,
	"iq4_xs": 1
	},
	"attn_v": {
	"q4_k": 5,
	"q5_k": 3
	},
	"ffn_down": {
	"iq2_s": 27,
	"iq4_xs": 2,
	"iq3_s": 2,
	"iq3_xxs": 1
	},
	"ffn_gate": {
	"iq2_s": 31,
	"iq4_xs": 1
	},
	"ffn_up": {
	"iq2_s": 23,
	"iq3_s": 8,
	"iq4_xs": 1
	},
	"ssm_out": {
	"iq4_xs": 23,
	"q5_k": 1
	}
	},
	"prior": "layout/prior.json",
	"pin_rule": "floor",
	"embd_cap": "heur",
	"generator": "auto_quant_v2.layout",
	"generator_key": "3bf8b43e20a68f0b",
	"quant_type": "IQ2_M",
	"quantize_ftype": "IQ2_M",
	"llama_cpp_version": "b11627",
	"unknown_kinds": {},
	"commit": "2d948bec8623bf6a14e732adb3400ec09ebb5e20"
	}