Instructions to use PeetPedro/qwen2.5-coder-32b-heretic-swe-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PeetPedro/qwen2.5-coder-32b-heretic-swe-sft with Transformers:

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

pipe = pipeline("text-generation", model="PeetPedro/qwen2.5-coder-32b-heretic-swe-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PeetPedro/qwen2.5-coder-32b-heretic-swe-sft")
model = AutoModelForCausalLM.from_pretrained("PeetPedro/qwen2.5-coder-32b-heretic-swe-sft", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use PeetPedro/qwen2.5-coder-32b-heretic-swe-sft with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="PeetPedro/qwen2.5-coder-32b-heretic-swe-sft",
	filename="gguf/qwen2.5-coder-32b-instruct-heretic.Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use PeetPedro/qwen2.5-coder-32b-heretic-swe-sft 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 PeetPedro/qwen2.5-coder-32b-heretic-swe-sft:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf PeetPedro/qwen2.5-coder-32b-heretic-swe-sft:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf PeetPedro/qwen2.5-coder-32b-heretic-swe-sft:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf PeetPedro/qwen2.5-coder-32b-heretic-swe-sft: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 PeetPedro/qwen2.5-coder-32b-heretic-swe-sft:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf PeetPedro/qwen2.5-coder-32b-heretic-swe-sft: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 PeetPedro/qwen2.5-coder-32b-heretic-swe-sft:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf PeetPedro/qwen2.5-coder-32b-heretic-swe-sft:Q4_K_M

Use Docker

docker model run hf.co/PeetPedro/qwen2.5-coder-32b-heretic-swe-sft:Q4_K_M

LM Studio
Jan

vLLM

How to use PeetPedro/qwen2.5-coder-32b-heretic-swe-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PeetPedro/qwen2.5-coder-32b-heretic-swe-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PeetPedro/qwen2.5-coder-32b-heretic-swe-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PeetPedro/qwen2.5-coder-32b-heretic-swe-sft:Q4_K_M

SGLang

How to use PeetPedro/qwen2.5-coder-32b-heretic-swe-sft 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 "PeetPedro/qwen2.5-coder-32b-heretic-swe-sft" \
    --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": "PeetPedro/qwen2.5-coder-32b-heretic-swe-sft",
		"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 "PeetPedro/qwen2.5-coder-32b-heretic-swe-sft" \
        --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": "PeetPedro/qwen2.5-coder-32b-heretic-swe-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use PeetPedro/qwen2.5-coder-32b-heretic-swe-sft with Ollama:
```
ollama run hf.co/PeetPedro/qwen2.5-coder-32b-heretic-swe-sft:Q4_K_M
```

Unsloth Studio

How to use PeetPedro/qwen2.5-coder-32b-heretic-swe-sft with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for PeetPedro/qwen2.5-coder-32b-heretic-swe-sft to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for PeetPedro/qwen2.5-coder-32b-heretic-swe-sft to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for PeetPedro/qwen2.5-coder-32b-heretic-swe-sft to start chatting

How to use PeetPedro/qwen2.5-coder-32b-heretic-swe-sft with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf PeetPedro/qwen2.5-coder-32b-heretic-swe-sft:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "PeetPedro/qwen2.5-coder-32b-heretic-swe-sft:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use PeetPedro/qwen2.5-coder-32b-heretic-swe-sft with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf PeetPedro/qwen2.5-coder-32b-heretic-swe-sft: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 PeetPedro/qwen2.5-coder-32b-heretic-swe-sft:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use PeetPedro/qwen2.5-coder-32b-heretic-swe-sft with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf PeetPedro/qwen2.5-coder-32b-heretic-swe-sft: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 "PeetPedro/qwen2.5-coder-32b-heretic-swe-sft: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"

Docker Model Runner
How to use PeetPedro/qwen2.5-coder-32b-heretic-swe-sft with Docker Model Runner:
```
docker model run hf.co/PeetPedro/qwen2.5-coder-32b-heretic-swe-sft:Q4_K_M
```

Lemonade

How to use PeetPedro/qwen2.5-coder-32b-heretic-swe-sft with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull PeetPedro/qwen2.5-coder-32b-heretic-swe-sft:Q4_K_M

Run and chat with the model

lemonade run user.qwen2.5-coder-32b-heretic-swe-sft-Q4_K_M

List all available models

lemonade list

qwen2.5-coder-32b-heretic-swe-sft

Stage sft output of an open abliterate → SFT → RFT → RLVR coding-model pipeline. Supervised fine-tuning (Unsloth LoRA) on agentic SWE + tool-calling data, on top of the abliterated base.

Base model: PeetPedro/qwen2.5-coder-32b-instruct-heretic
Chat format: ChatML (Qwen)
Pipeline: https://github.com/entropy-om/heretic-coder-pipeline

Evaluation

Metric	Value
`refusal_rate`	0.0000
`train_loss`	0.3318
`bfcl_accuracy`	0.3083
`humaneval_delta`	-0.1159
`swebench_resolve`	1.0000

Intended use & responsible use

This model is abliterated (uncensored). Refusal behaviour has been deliberately reduced, so it will not reliably decline unsafe or disallowed requests. It is intended for internal, gated engineering use behind verify-before-merge and your own moderation / authorization layer — never user-facing without an independent safety layer. Weights are private / gated. You own the outputs; use it lawfully.

Provenance

Built with Heretic (abliteration), Unsloth + TRL (SFT/RFT/RLVR). See the pipeline repo for the exact stage configs, gates, and the reproducible harness.

No benchmark numbers are claimed beyond the table above; evaluate on your own tasks.