Instructions to use llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use llmfan46/Ornith-1.0-35B-uncensored-heretic-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 llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf llmfan46/Ornith-1.0-35B-uncensored-heretic-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 llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf llmfan46/Ornith-1.0-35B-uncensored-heretic-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 llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf llmfan46/Ornith-1.0-35B-uncensored-heretic-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 llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF:Q4_K_M

Use Docker

docker model run hf.co/llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "llmfan46/Ornith-1.0-35B-uncensored-heretic-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": "llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF:Q4_K_M

SGLang

How to use llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF 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 "llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF" \
    --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": "llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF",
		"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 "llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF" \
        --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": "llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF with Ollama:
```
ollama run hf.co/llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF:Q4_K_M
```
Unsloth Desktop

How to use llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf llmfan46/Ornith-1.0-35B-uncensored-heretic-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": "llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF with Docker Model Runner:
```
docker model run hf.co/llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF:Q4_K_M
```

Lemonade

How to use llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Ornith-1.0-35B-uncensored-heretic-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use llmfan46/Ornith-1.0-35B-uncensored-heretic-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 llmfan46/Ornith-1.0-35B-uncensored-heretic-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 llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf llmfan46/Ornith-1.0-35B-uncensored-heretic-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 "llmfan46/Ornith-1.0-35B-uncensored-heretic-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"

终于等到heretic版了，测试了一下. llama.cpp perplexity

by xht033 - opened Jul 1

Discussion

xht033

Jul 1

   # Perplexity Benchmark — wikitext-2 (wiki.test.raw)

   ## Setup

   - Dataset: wikitext-2 raw test set (wiki.test.raw)
   - Chunks: 4 x 2048 = 8192 tokens
   - Flags: -ngl 999 -b 512 --chunks 4 -fa on
   - Quantization: Q4_K_M for all models
   - Tool: llama-perplexity from llama.cpp

   ## Models

   | # | Model | Source |
   |---|-------|--------|
   | 1 | Qwen3.6-35B-A3B-uncensored-heretic (Native-MTP) | llmfan46 |
   | 2 | Qwen3.6-35B-A3B-uncensored-heretic (base) | llmfan46 |
   | 3 | Ornith-1.0-35B-Q4_K_M | bartowski |
   | 4 | Ornith-1.0-35B-uncensored-heretic-Q4_K_M | llmfan46 |

   ## Results (lower = better)

   | Rank | Model | Perplexity | Size |
   |------|-------|-----------|------|
   | 1 | Qwen3.6-35B-A3B-uncensored-heretic (Native-MTP) | 6.2599 | 20G |
   | 2 | Qwen3.6-35B-A3B-uncensored-heretic (base) | 6.2834 | 20G |
   | 3 | Ornith-1.0-35B (bartowski) | 6.3405 | 20G |
   | 4 | Ornith-1.0-35B-uncensored-heretic (llmfan46) | 6.5624 | 20G |

   ## Observations

   - Qwen3.6-35B-A3B MTP leads with 6.26 PPL, marginally ahead of the non-MTP version (6.28).
   - Both Ornith-1.0-35B variants sit behind Qwen3.6-35B-A3B by ~0.08-0.30 PPL points.
   - The bartowski Ornith (6.34) beats the llmfan46 heretic Ornith (6.56) by ~0.22 PPL.

   Question: is this gap meaningful given wikitext-2 is a narrow benchmark?

llmfan46

Owner Jul 1

•

edited Jul 1

Well then better to use the Qwen3.6-35B-A3B-uncensored-heretic (Native-MTP) version then since it scores the best?

Also bartowski scores better but it is the censored version , even on my benchmark you can see that I tested the original censored version and my uncensored version, here are the test scores:

MMLU test results:

Original:

============================================================

Total questions: 7021

Correct: 5802

Accuracy: 0.8264 (82.64%)

Parse failures: 0

============================================================

Heretic:

============================================================

Total questions: 7021

Correct: 5737

Accuracy: 0.8171 (81.71%)

Parse failures: 0

============================================================

You can see that there is an accuracy loss of 0.93%.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment