Instructions to use SkyIsNotGreen/hive-auditor-1.7b-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SkyIsNotGreen/hive-auditor-1.7b-v1 with Transformers:

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

pipe = pipeline("text-generation", model="SkyIsNotGreen/hive-auditor-1.7b-v1")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SkyIsNotGreen/hive-auditor-1.7b-v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use SkyIsNotGreen/hive-auditor-1.7b-v1 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 SkyIsNotGreen/hive-auditor-1.7b-v1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf SkyIsNotGreen/hive-auditor-1.7b-v1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SkyIsNotGreen/hive-auditor-1.7b-v1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf SkyIsNotGreen/hive-auditor-1.7b-v1:Q4_K_M

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 SkyIsNotGreen/hive-auditor-1.7b-v1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf SkyIsNotGreen/hive-auditor-1.7b-v1:Q4_K_M

Use Docker

docker model run hf.co/SkyIsNotGreen/hive-auditor-1.7b-v1:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use SkyIsNotGreen/hive-auditor-1.7b-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/SkyIsNotGreen/hive-auditor-1.7b-v1:Q4_K_M

SGLang

How to use SkyIsNotGreen/hive-auditor-1.7b-v1 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 "SkyIsNotGreen/hive-auditor-1.7b-v1" \
    --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": "SkyIsNotGreen/hive-auditor-1.7b-v1",
		"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 "SkyIsNotGreen/hive-auditor-1.7b-v1" \
        --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": "SkyIsNotGreen/hive-auditor-1.7b-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use SkyIsNotGreen/hive-auditor-1.7b-v1 with Ollama:
```
ollama run hf.co/SkyIsNotGreen/hive-auditor-1.7b-v1:Q4_K_M
```
Unsloth Desktop

How to use SkyIsNotGreen/hive-auditor-1.7b-v1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SkyIsNotGreen/hive-auditor-1.7b-v1: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": "SkyIsNotGreen/hive-auditor-1.7b-v1:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use SkyIsNotGreen/hive-auditor-1.7b-v1 with Docker Model Runner:
```
docker model run hf.co/SkyIsNotGreen/hive-auditor-1.7b-v1:Q4_K_M
```

Lemonade

How to use SkyIsNotGreen/hive-auditor-1.7b-v1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SkyIsNotGreen/hive-auditor-1.7b-v1:Q4_K_M

Run and chat with the model

lemonade run user.hive-auditor-1.7b-v1-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use SkyIsNotGreen/hive-auditor-1.7b-v1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SkyIsNotGreen/hive-auditor-1.7b-v1: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 SkyIsNotGreen/hive-auditor-1.7b-v1:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use SkyIsNotGreen/hive-auditor-1.7b-v1 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SkyIsNotGreen/hive-auditor-1.7b-v1: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 "SkyIsNotGreen/hive-auditor-1.7b-v1: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"

Hive Auditor 1.7B

The Hive 1.7B roster

This model is one seat in the five-model Hive 1.7B family. They are role specialists, not five general chat models:

model	seats
Hive Conductor 1.7B	controller + planner
Hive Reader 1.7B	mechanics + RAG
Hive Auditor 1.7B	placement + critic
Hive Dispatcher 1.7B	dispatcher
Hive Tool Manager 1.7B	agency

The family is served and routed by Hive.

A placement + critic specialist for the Hive local control plane: decide where models fit, and check whether a proposed assignment or schedule is valid.

Built from LiquidAI/LFM3-1.7B-Base, this specialist covers the placement and critic seats. It is not a general chat model.

Use cases

Will this model fit? Given weights, runtime reserve, KV cache per 8k block and a card's total memory, return how many whole context blocks fit.
Card placement. Choose the smallest card that fits a model, or assign several models to cards under a memory budget.
Preflight a proposed plan. Validate an assignment, schedule or order before the dispatcher or harness executes it, and answer yes/no.
Capacity audits. Check batch jobs, model tiers or context windows against the memory a local machine actually has.
Guardrail for the other seats. Use the critic output as a cheap second check on a Conductor or Dispatcher plan.

Auditor is the placement/critic seat. It checks fit and validity; it does not run the plan or act as a general chat model.

Evaluation

Held-out Hive role suites, greedy decoding:

role	path	accuracy	n	median
placement	HF	0.957	46	0.036 s
placement	GGUF	0.935	46	0.047 s
critic	HF	0.947	38	0.038 s
critic	GGUF	0.921	38	0.057 s

Reproduce

The held-out task files, deterministic checkers and endpoint evaluator are in the Hive harness. The JSON files under eval/ are the exact evaluation records: greedy decoding, response_format enabled for JSON-shaped tasks, and Q4_K_M for the GGUF row. Weight hashes are in SHA256SUMS.

Training

Base: LiquidAI/LFM3-1.7B-Base
Method: TRL SFT + LoRA (r=16, alpha=32, dropout 0.05)
Data: synthetic, checker-validated Hive role rows; no user data
Format: LFM3 chat template with enable_thinking=false; assistant-only loss
Run: 2600 rows, 3.0 epochs, 489 steps
Peak VRAM: 13.9 GiB on one 20 GB AMD card

Usage

Merged transformers model:

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "SkyIsNotGreen/hive-auditor-1.7b-v1"
model = AutoModelForCausalLM.from_pretrained(
    repo, subfolder="model", dtype="bfloat16", trust_remote_code=True)
tok = AutoTokenizer.from_pretrained(
    repo, subfolder="model", trust_remote_code=True)

PEFT adapter:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base = AutoModelForCausalLM.from_pretrained(
    "LiquidAI/LFM3-1.7B-Base", dtype="bfloat16", trust_remote_code=True)
model = PeftModel.from_pretrained(base, "SkyIsNotGreen/hive-auditor-1.7b-v1", subfolder="adapter")

GGUF with llama.cpp:

llama-server -m gguf/hive-auditor-1.7b-v1-Q4_K_M.gguf --alias auditor-1.7b \
  --host 127.0.0.1 --port 8162 -ngl 999 -c 8192 -np 2 \
  --jinja --reasoning off --no-webui

--reasoning off is required for this LFM3 template.

Run with Hive

hive serve can fetch this GGUF and start it as a role tier; see the Hive install guide. The direct llama-server command above is the minimal portable path.

Limitations

Placement assigns models to cards under VRAM/KV budgets; critic validates assignments, schedules, and orders. The model is not a general chat model; use a deterministic checker in production.

License and attribution

This is a derivative of LiquidAI/LFM3-1.7B-Base, released under the LFM Open License v1.0 (see LICENSE). The base model is by Liquid AI. Commercial use by an entity above USD 10M annual revenue is not licensed under LFM 1.0.

Modified files: the LoRA adapter, merged weights, and GGUF conversion. See NOTICE.

Downloads last month: 30

GGUF

Model size

2B params

Architecture

lfm3

Hardware compatibility

4-bit

Model tree for SkyIsNotGreen/hive-auditor-1.7b-v1

Base model

LiquidAI/LFM3-1.7B-Base

Adapter

(7)

this model

Collection including SkyIsNotGreen/hive-auditor-1.7b-v1

Hive series

Collection

The fine-tuned controllers, encoders and decision models that make the Hive harness work. • 6 items • Updated 4 days ago