Instructions to use notfakerv/round2-1.7b-loop-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use notfakerv/round2-1.7b-loop-preview 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 notfakerv/round2-1.7b-loop-preview:BF16
# Run inference directly in the terminal:
llama cli -hf notfakerv/round2-1.7b-loop-preview:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf notfakerv/round2-1.7b-loop-preview:BF16
# Run inference directly in the terminal:
llama cli -hf notfakerv/round2-1.7b-loop-preview:BF16

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf notfakerv/round2-1.7b-loop-preview:BF16
# Run inference directly in the terminal:
./build/bin/llama cli -hf notfakerv/round2-1.7b-loop-preview:BF16

Use Docker

docker model run hf.co/notfakerv/round2-1.7b-loop-preview:BF16

Llama new
LM Studio
Jan

vLLM

How to use notfakerv/round2-1.7b-loop-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "notfakerv/round2-1.7b-loop-preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "notfakerv/round2-1.7b-loop-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/notfakerv/round2-1.7b-loop-preview:BF16

Ollama
How to use notfakerv/round2-1.7b-loop-preview with Ollama:
```
ollama run hf.co/notfakerv/round2-1.7b-loop-preview:BF16
```
Unsloth Desktop

How to use notfakerv/round2-1.7b-loop-preview with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf notfakerv/round2-1.7b-loop-preview:BF16

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": "notfakerv/round2-1.7b-loop-preview:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use notfakerv/round2-1.7b-loop-preview with Docker Model Runner:
```
docker model run hf.co/notfakerv/round2-1.7b-loop-preview:BF16
```

Lemonade

How to use notfakerv/round2-1.7b-loop-preview with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull notfakerv/round2-1.7b-loop-preview:BF16

Run and chat with the model

lemonade run user.round2-1.7b-loop-preview-BF16

List all available models

lemonade list

Hermes Agent

How to use notfakerv/round2-1.7b-loop-preview with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf notfakerv/round2-1.7b-loop-preview:BF16

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 notfakerv/round2-1.7b-loop-preview:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use notfakerv/round2-1.7b-loop-preview with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf notfakerv/round2-1.7b-loop-preview:BF16

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 "notfakerv/round2-1.7b-loop-preview:BF16" \
  --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"

round2-1.7b-loop-preview / validation /native-vs-pytorch.json

notfakerv

round2-1.7b-loop-preview: looped LFM3-1.7B after two expert-iteration rounds

d6729d5 verified 1 day ago

Raw History Blame Contribute Delete

3.01 kB

{"note": "round2 GGUF on the patched llama.cpp (CUDA, flash attention) against the PyTorch reference in BF16, teacher-forced on 4 prompts (two held-out questions and two chat prompts) plus 160-token continuations. Stock LFM3-1.7B through the same paths gives the noise floor. kl_* are mean/max KL(PyTorch || native) per position; loop_effect_* compare (round2 - stock) logits between the two implementations.", "cases": [{"case": 0, "prompt": 279, "continuation": 160, "top1_round2_native_vs_torch": 1.0, "top1_stock_native_vs_torch": 1.0, "kl_round2_mean": 0.0001426682820327905, "kl_round2_max": 0.0028068692658116965, "kl_stock_mean": 0.0001609368648454506, "kl_stock_max": 0.0029377103012698624, "kl_round2_vs_stock_torch": 0.0055928715270120374, "kl_round2_vs_stock_native": 0.005659226750984238, "loop_effect_corr_median": 0.9942394948423594, "loop_effect_corr_min": 0.9765317580917701, "loop_effect_rel_err_median": 0.061895884573459625, "batch_vs_step_max_abs": 0.14734220504760742, "batch_vs_step_top1": 1.0, "greedy_tokens_matching_torch": 7}, {"case": 1, "prompt": 183, "continuation": 160, "top1_round2_native_vs_torch": 1.0, "top1_stock_native_vs_torch": 0.99375, "kl_round2_mean": 0.0002778435430767569, "kl_round2_max": 0.004878883315494113, "kl_stock_mean": 0.00024310277751130464, "kl_stock_max": 0.004015256609590341, "kl_round2_vs_stock_torch": 0.0047618559924853185, "kl_round2_vs_stock_native": 0.004309408853861823, "loop_effect_corr_median": 0.9920087966590755, "loop_effect_corr_min": 0.9618845090214068, "loop_effect_rel_err_median": 0.0853118896484375, "batch_vs_step_max_abs": 0.19392919540405273, "batch_vs_step_top1": 1.0, "greedy_tokens_matching_torch": 49}, {"case": 2, "prompt": 19, "continuation": 149, "top1_round2_native_vs_torch": 0.9932885906040269, "top1_stock_native_vs_torch": 0.9932885906040269, "kl_round2_mean": 0.00011761379324040443, "kl_round2_max": 0.003203415557652076, "kl_stock_mean": 0.00012247408744256143, "kl_stock_max": 0.0020579289922198294, "kl_round2_vs_stock_torch": 0.0018858596279993515, "kl_round2_vs_stock_native": 0.001999329106619821, "loop_effect_corr_median": 0.9888921236023356, "loop_effect_corr_min": 0.9747341327697195, "loop_effect_rel_err_median": 0.12492570281028748, "batch_vs_step_max_abs": 0.12328943610191345, "batch_vs_step_top1": 1.0, "greedy_tokens_matching_torch": 19}, {"case": 3, "prompt": 22, "continuation": 160, "top1_round2_native_vs_torch": 0.99375, "top1_stock_native_vs_torch": 0.99375, "kl_round2_mean": 0.00022004322433143256, "kl_round2_max": 0.0015516938132002476, "kl_stock_mean": 0.0002039846516787163, "kl_stock_max": 0.002621586720236445, "kl_round2_vs_stock_torch": 0.004584524303704871, "kl_round2_vs_stock_native": 0.004323844994894231, "loop_effect_corr_median": 0.9926694311395783, "loop_effect_corr_min": 0.9754868229966214, "loop_effect_rel_err_median": 0.10051585733890533, "batch_vs_step_max_abs": 0.1692945957183838, "batch_vs_step_top1": 0.9937888198757764, "greedy_tokens_matching_torch": 39}]}