Text Generation
llama-cpp-python
GGUF
English
code-generation
coding-assistant
llama.cpp
qwen2.5
python
javascript
fine-tuned
conversational
Instructions to use neuralbroker/blitzkode with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use neuralbroker/blitzkode with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="neuralbroker/blitzkode", filename="blitzkode.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - llama-cpp-python
How to use neuralbroker/blitzkode with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="neuralbroker/blitzkode", filename="blitzkode.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use neuralbroker/blitzkode with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf neuralbroker/blitzkode # Run inference directly in the terminal: llama-cli -hf neuralbroker/blitzkode
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf neuralbroker/blitzkode # Run inference directly in the terminal: llama-cli -hf neuralbroker/blitzkode
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 neuralbroker/blitzkode # Run inference directly in the terminal: ./llama-cli -hf neuralbroker/blitzkode
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 neuralbroker/blitzkode # Run inference directly in the terminal: ./build/bin/llama-cli -hf neuralbroker/blitzkode
Use Docker
docker model run hf.co/neuralbroker/blitzkode
- LM Studio
- Jan
- vLLM
How to use neuralbroker/blitzkode with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "neuralbroker/blitzkode" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "neuralbroker/blitzkode", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/neuralbroker/blitzkode
- Ollama
How to use neuralbroker/blitzkode with Ollama:
ollama run hf.co/neuralbroker/blitzkode
- Unsloth Studio new
How to use neuralbroker/blitzkode 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 neuralbroker/blitzkode 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 neuralbroker/blitzkode to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for neuralbroker/blitzkode to start chatting
- Pi new
How to use neuralbroker/blitzkode with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf neuralbroker/blitzkode
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": "neuralbroker/blitzkode" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use neuralbroker/blitzkode with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf neuralbroker/blitzkode
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 neuralbroker/blitzkode
Run Hermes
hermes
- Docker Model Runner
How to use neuralbroker/blitzkode with Docker Model Runner:
docker model run hf.co/neuralbroker/blitzkode
- Lemonade
How to use neuralbroker/blitzkode with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull neuralbroker/blitzkode
Run and chat with the model
lemonade run user.blitzkode-{{QUANT_TAG}}List all available models
lemonade list
| #!/usr/bin/env python3 | |
| """Push all BlitzKode artifacts to HuggingFace Hub in one command. | |
| Uploads | |
| ------- | |
| 1. LoRA adapter (1.5B) → neuralbroker/blitzkode-1.5b-lora | |
| 2. LoRA adapter (0.5B) → neuralbroker/blitzkode-lora-0.5b | |
| 3. GGUF model file → neuralbroker/blitzkode (into a GGUF-specific branch/folder) | |
| Usage | |
| ----- | |
| # Export HF_TOKEN first, then run: | |
| python scripts/push_all_to_hub.py | |
| # Or pass token directly: | |
| python scripts/push_all_to_hub.py --token hf_XXXX | |
| # Dry-run to validate without pushing: | |
| python scripts/push_all_to_hub.py --dry-run | |
| """ | |
| from __future__ import annotations | |
| import argparse | |
| import os | |
| import subprocess | |
| import sys | |
| from pathlib import Path | |
| REPO_ROOT = Path(__file__).resolve().parents[1] | |
| PUSH_SCRIPT = REPO_ROOT / "scripts" / "push_to_hub.py" | |
| ARTIFACTS = [ | |
| { | |
| "label": "1.5B LoRA adapter (primary)", | |
| "checkpoint": REPO_ROOT / "checkpoints" / "blitzkode-1.5b-lora" / "final", | |
| "repo_id": "neuralbroker/blitzkode-1.5b-lora", | |
| "commit_message": "Upload BlitzKode 1.5B LoRA adapter v2.1 (100-step SFT)", | |
| }, | |
| { | |
| "label": "0.5B LoRA adapter (lightweight)", | |
| "checkpoint": REPO_ROOT / "checkpoints" / "available-lora-0.5b-full" / "final", | |
| "repo_id": "neuralbroker/blitzkode-lora-0.5b", | |
| "commit_message": "Upload BlitzKode 0.5B LoRA adapter v2.1 (50-step SFT)", | |
| }, | |
| ] | |
| def push_gguf(token: str, gguf_path: Path, dry_run: bool) -> None: | |
| if not gguf_path.exists(): | |
| print(f" [SKIP] GGUF not found: {gguf_path}") | |
| return | |
| size_gb = gguf_path.stat().st_size / 1024 ** 3 | |
| print(f"\n Uploading GGUF ({size_gb:.2f} GB) → neuralbroker/blitzkode ...") | |
| if dry_run: | |
| print(" [DRY RUN] skipped.") | |
| return | |
| from huggingface_hub import HfApi # noqa: PLC0415 | |
| from huggingface_hub.utils import HfHubHTTPError # noqa: PLC0415 | |
| api = HfApi(token=token) | |
| try: | |
| api.create_repo("neuralbroker/blitzkode", repo_type="model", exist_ok=True) | |
| api.upload_file( | |
| path_or_fileobj=str(gguf_path), | |
| path_in_repo="blitzkode.gguf", | |
| repo_id="neuralbroker/blitzkode", | |
| repo_type="model", | |
| commit_message="Update GGUF model Q8_0 (1.5B merged + quantised)", | |
| ) | |
| print(" [OK] GGUF uploaded → https://huggingface.co/neuralbroker/blitzkode") | |
| except HfHubHTTPError as exc: | |
| print(f" [ERROR] GGUF upload failed: {exc}", file=sys.stderr) | |
| def main() -> None: | |
| parser = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter) | |
| parser.add_argument("--token", default=os.environ.get("HF_TOKEN", ""), help="HuggingFace write token (or set HF_TOKEN env var).") | |
| parser.add_argument("--dry-run", action="store_true", help="Validate only, do not push.") | |
| args = parser.parse_args() | |
| token = args.token.strip() | |
| if not token and not args.dry_run: | |
| print( | |
| "\n[ERROR] HuggingFace token required.\n" | |
| " Option 1: export HF_TOKEN=hf_XXXX\n" | |
| " Option 2: python scripts/push_all_to_hub.py --token hf_XXXX\n" | |
| " Option 3: run --dry-run to validate without pushing\n" | |
| "\nGet a write token at: https://huggingface.co/settings/tokens", | |
| file=sys.stderr, | |
| ) | |
| sys.exit(1) | |
| print("=" * 72) | |
| print("BLITZKODE — PUSH ALL ARTIFACTS TO HUGGING FACE HUB") | |
| if args.dry_run: | |
| print("(DRY RUN — nothing will be pushed)") | |
| print("=" * 72) | |
| failures: list[str] = [] | |
| for art in ARTIFACTS: | |
| print(f"\n{'─' * 60}") | |
| print(f" Artifact : {art['label']}") | |
| print(f" Repo : {art['repo_id']}") | |
| checkpoint: Path = art["checkpoint"] | |
| if not checkpoint.exists(): | |
| print(f" [SKIP] Checkpoint not found: {checkpoint}") | |
| continue | |
| cmd = [ | |
| sys.executable, | |
| str(PUSH_SCRIPT), | |
| "--checkpoint", | |
| str(checkpoint), | |
| "--repo-id", | |
| art["repo_id"], | |
| "--commit-message", | |
| art["commit_message"], | |
| ] | |
| if args.dry_run: | |
| cmd.append("--dry-run") | |
| if token: | |
| cmd += ["--token", token] | |
| result = subprocess.run(cmd) | |
| if result.returncode != 0: | |
| failures.append(art["repo_id"]) | |
| print(f" [FAIL] Push exited with code {result.returncode}", file=sys.stderr) | |
| # GGUF upload (direct via huggingface_hub) | |
| print(f"\n{'─' * 60}") | |
| print(" Artifact : GGUF model (neuralbroker/blitzkode)") | |
| if not args.dry_run and token: | |
| push_gguf(token, REPO_ROOT / "blitzkode.gguf", dry_run=False) | |
| else: | |
| push_gguf(token, REPO_ROOT / "blitzkode.gguf", dry_run=True) | |
| # Summary | |
| print(f"\n{'=' * 72}") | |
| if failures: | |
| print(f"PUSH FINISHED WITH FAILURES: {failures}") | |
| sys.exit(1) | |
| else: | |
| print("ALL PUSHES COMPLETE") | |
| print("\nHuggingFace repos:") | |
| for art in ARTIFACTS: | |
| print(f" https://huggingface.co/{art['repo_id']}") | |
| print(" https://huggingface.co/neuralbroker/blitzkode (GGUF)") | |
| if __name__ == "__main__": | |
| main() | |