Instructions to use Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS with Transformers:

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

pipe = pipeline("text-generation", model="Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS")
model = AutoModelForCausalLM.from_pretrained("Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS 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 Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS: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 Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS: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 Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS:Q4_K_M

Use Docker

docker model run hf.co/Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS:Q4_K_M

SGLang

How to use Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS 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 "Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS" \
    --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": "Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS",
		"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 "Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS" \
        --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": "Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS with Ollama:
```
ollama run hf.co/Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS:Q4_K_M
```
Unsloth Desktop

How to use Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS: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": "Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS with Docker Model Runner:
```
docker model run hf.co/Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS:Q4_K_M
```

Lemonade

How to use Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS:Q4_K_M

Run and chat with the model

lemonade run user.ozyvler-Ozygram-Neural-7B-Coder-MCTS-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS: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 Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS: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 "Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS: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"

🧠 Ozygram Neural 7B (Dream-RSI & Kev Engine) v2

A Local Neuro-Symbolic Model for Autonomous Code Self-Healing, AST Mutative Repair, and Transactional Integrity.

📌 Model Overview

Ozygram Neural 7B v2 is a specialized, open-weights code intelligence model engineered for autonomous local self-healing, automated bug localization, and high-concurrency transactional software engineering.

Trained natively on local GPU hardware via QLoRA over curated neuro-symbolic contracts, it introduces a dual-phase execution architecture:

Dream-RSI (Recursive Self-Improvement & MCTS): An internal reasoning chain enclosed within <|thought_start|> and <|thought_end|>. It mentally explores candidate AST trajectories, simulates execution graphs, evaluates blast radius across dependent files, detects concurrency deadlocks, and discards naive or destructive paths before committing code.
Kev Action Engine: A zero-prose, deterministic JSON action protocol (ast_mutation and apply_patch), delivering atomic target/replacement hunks directly to IDEs and autonomous runtime agents without conversational hallucinations or fragile line offsets.

🏗️ Architecture & Philosophy

               [ User Incident / Pytest Failure / Production Traceback ]
                                    │
                                    ▼
       ┌────────────────────────────────────────────────────────┐
       │               Ozygram Neural Orchestrator              │
       │                                                        │
       │  Phase 1: Dream-RSI (Internal Monte Carlo Tree Search) │
       │  <|thought_start|>                                     │
       │   - Parse Error Spectrum & Root Cause                  │
       │   - Validate AST Graph Dependency (Blast Radius)       │
       │   - Discard Naive / Destructive Branches (-1.0 score)  │
       │   - Simulate Transactional Rollback & Concurrency Paths│
       │  <|thought_end|>                                       │
       │                                                        │
       │  Phase 2: Kev Action Engine (Deterministic JSON)       │
       │  {                                                     │
       │    "action": "ast_mutation" | "apply_patch",           │
       │    "target_files": [...],                              │
       │    "blast_radius_validated": true,                     │
       │    "target": "faulty_code_snippet",                    │
       │    "replacement": "surgical_repaired_code"             │
       │  }                                                     │
       └────────────────────────────────────────────────────────┘
                                    │
                                    ▼
       [ IDE / Continue / VS Code / Kev AST Engine: Live Patch ]

📈 Training Metrics & Convergence

Base Model: Qwen/Qwen2.5-7B-Instruct
Training Method: 4-bit NormalFloat (NF4) QLoRA + Paged AdamW 8-bit + Gradient Checkpointing
Total Epochs: 3.0 / 3.0 (450 optimization steps)
Final Training Loss: 0.005904 (steady monotonic descent from 0.082 initial)
Mean Token Accuracy: >99.4%
Gradient Norm: 0.044 (zero gradient explosion, stable convergence)
Hardware: NVIDIA Quadro RTX 4000 Max-Q (8 GB VRAM), Windows WDDM Desktop primary display.

📊 Benchmark & Real-World Validation

1. Master Gym Benchmark Suite (100% Pass)

Gym 1: The Blast Radius Challenge — Native AST dependency graph traversal without brute-force file crawling (5/5 PASS - 100%).
Gym 2: The Infinite Loop Simulation — Concurrency deadlocks, semaphore leaks, and transactional rollback (5/5 PASS - 100%).
Gym 3: The Speculative Speedrun — High-throughput boilerplate delegation (5/5 PASS - 100%).

2. Live Local CRM Self-Healing Benchmark (`crmgeofa-localdev`)

Evaluated directly on an enterprise ERP/CRM codebase containing >40 modules, asynchronous export workers, and high-concurrency Excel report generation:

Mutated Production Bug	Root Cause Injected	Diagnosis	Action Protocol	Status
`MUT_01_EXPORT_PREFIX`	Missing mandatory `N-` prefix in report filenames	100%	`ast_mutation`	✅ PASS
`MUT_02_ALPHA_SAMPLE_REGEX`	Corrupted regex `[0-9]+$` on alphanumeric samples	100%	`ast_mutation`	✅ PASS
`MUT_03_QUOTE_DATE_PARSER`	Inverted day/month in strict ISO date validator	100%	`ast_mutation`	✅ PASS
`MUT_05_EXCEL_DIV_ZERO`	Zero-division crash (`dry_net <= 0`) in moisture math	100%	`ast_mutation`	✅ PASS
`MUT_06_WORKER_LEAK_DEADLOCK`	Unreleased semaphore lock in rollback exception handler	100%	`ast_mutation`	✅ PASS

⚡ Prompt Contract & Prefix Caching

To guarantee 100% Prefix Caching (zero prefill latency on local GPUs), queries must adhere to the immutable contract:

<|im_start|>system
[CONTRATO OZYGRAM NEURAL V1]
- Arquitectura: Neuro-Simbólica Local.
- Salida del Razonamiento Interno: Entre <|thought_start|> y <|thought_end|>.
- Formato de Acción (Kev Engine): JSON estructural estricto sin prosa externa.
- Herramientas AST nativas mapeadas en memoria: [Engram_O1_Definitions]
<|im_end|>
<|im_start|>user
{error_traceback_and_code_context}
<|im_end|>
<|im_start|>assistant
<|thought_start|>
[MCTS Diagnóstico de Producción: ...]
  -> Verificando AST y ramas semánticas...
[MCTS Backtrack: Descartando soluciones ingenuas...]
[Conclusión Dream-RSI: Transmitiendo acción JSON de Kev Engine...]
<|thought_end|>
{
  "action": "ast_mutation",
  "target_files": ["app/workers/export_worker.py"],
  "blast_radius_validated": true,
  "target": "finally:\n            pass",
  "replacement": "finally:\n            self.semaphore.release()",
  "execution_status": "ready"
}
<|im_end|>

💻 How to Run

1. In Ollama (Recommended)

Download the quantized GGUF (ozygram-qwen7b-Q4_K_M.gguf) and create the model:

ollama create ozygram -f Modelfile
ollama run ozygram

Modelfile:

FROM ./ozygram-qwen7b-Q4_K_M.gguf

PARAMETER temperature 0.2
PARAMETER top_p 0.95
PARAMETER repeat_penalty 1.1
PARAMETER stop "<|im_end|>"

TEMPLATE """{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ else }}<|im_start|>system
[CONTRATO OZYGRAM NEURAL V1]
- Arquitectura: Neuro-Simbólica Local.
- Salida del Razonamiento Interno: Entre <|thought_start|> y <|thought_end|>.
- Formato de Acción (Kev Engine): JSON estructural estricto sin prosa externa.
- Herramientas AST nativas mapeadas en memoria: [Engram_O1_Definitions]
<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
{{ .Response }}<|im_end|>"""

2. In Transformers (Python)

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

⚙️ Hardware Profile & Quantization

Quantization	File Size	GPU VRAM	Recommended Device
`Q4_K_M`	4.36 GB	~4.6 GB	Laptops & Workstations (Quadro RTX 4000, RTX 3060/4060 8GB)
`Q8_0`	~7.5 GB	~8.2 GB	Desktop GPU (12GB+ VRAM)
`BF16`	14.5 GB	~16 GB	Cloud / Multi-GPU Server (A10G, L4, A100)

📜 Citation

@misc{ozygram_neural_v2_2026,
  author = {Ozygram Research & Autonomous Engineering Team},
  title = {Ozygram Neural v2: Local Neuro-Symbolic MCTS Model for Autonomous Code Self-Healing},
  year = {2026},
  publisher = {Hugging Face},
  howpublished = {\url{https://huggingface.co/Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS}}
}

Downloads last month: 846

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Quantized

(442)

this model

Quantizations

2 models

🧠 Ozygram Neural 7B (Dream-RSI & Kev Engine) v2

📌 Model Overview

🏗️ Architecture & Philosophy

📈 Training Metrics & Convergence

📊 Benchmark & Real-World Validation

1. Master Gym Benchmark Suite (100% Pass)

2. Live Local CRM Self-Healing Benchmark (crmgeofa-localdev)

⚡ Prompt Contract & Prefix Caching

💻 How to Run

1. In Ollama (Recommended)

2. In Transformers (Python)

⚙️ Hardware Profile & Quantization

📜 Citation

Model tree for Xangel0s/ozyvler-Ozygram-Neural-7B-Coder-MCTS

2. Live Local CRM Self-Healing Benchmark (`crmgeofa-localdev`)