Text Generation
Transformers
Safetensors
qwen2
godot
gdscript
qlora
game-development
conversational
text-generation-inference
Instructions to use khursheed/VibeGame-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use khursheed/VibeGame-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="khursheed/VibeGame-8B") 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("khursheed/VibeGame-8B") model = AutoModelForCausalLM.from_pretrained("khursheed/VibeGame-8B", 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
- vLLM
How to use khursheed/VibeGame-8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "khursheed/VibeGame-8B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "khursheed/VibeGame-8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/khursheed/VibeGame-8B
- SGLang
How to use khursheed/VibeGame-8B 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 "khursheed/VibeGame-8B" \ --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": "khursheed/VibeGame-8B", "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 "khursheed/VibeGame-8B" \ --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": "khursheed/VibeGame-8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use khursheed/VibeGame-8B with Docker Model Runner:
docker model run hf.co/khursheed/VibeGame-8B
Download code/tests/test_continue_run.py from khursheed/VibeGame-8B: direct link, hf CLI and curl.
- Browser
- Download file 3.62 kB
-
https://huggingface.co/khursheed/VibeGame-8B/resolve/main/code/tests/test_continue_run.py
- Command line
-
hf download hf://khursheed/VibeGame-8B/code/tests/test_continue_run.py
-
curl -L -o test_continue_run.py https://huggingface.co/khursheed/VibeGame-8B/resolve/main/code/tests/test_continue_run.py
3.62 kB
| """Continuation lifecycle checks without GPUs, engines, or running subprocesses.""" | |
| import json | |
| from pathlib import Path | |
| import sys | |
| import tempfile | |
| from types import SimpleNamespace | |
| import unittest | |
| from unittest.mock import Mock | |
| sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "scripts")) | |
| import continue_run | |
| class NoSuchProcess(Exception): | |
| pass | |
| class ContinuationTests(unittest.TestCase): | |
| def test_nonchild_zombie_does_not_wait_for_notebook_reaping(self): | |
| process = Mock() | |
| process.status.side_effect = ["running", "running", "zombie"] | |
| process.cmdline.return_value = ["python", "scripts/train.py"] | |
| process.is_running.return_value = True | |
| psutil = SimpleNamespace(Process=Mock(return_value=process), | |
| STATUS_ZOMBIE="zombie", NoSuchProcess=NoSuchProcess) | |
| sleep = Mock() | |
| continue_run.wait_for_training_process(123, psutil, sleep=sleep) | |
| sleep.assert_called_once_with(2) | |
| process.wait.assert_not_called() | |
| def test_already_exited_training_and_pid_reuse(self): | |
| psutil = SimpleNamespace(Process=Mock(side_effect=NoSuchProcess), | |
| STATUS_ZOMBIE="zombie", NoSuchProcess=NoSuchProcess) | |
| continue_run.wait_for_training_process(123, psutil, sleep=Mock()) | |
| process = Mock() | |
| process.status.return_value = "running" | |
| process.cmdline.return_value = ["unrelated", "command"] | |
| psutil.Process = Mock(return_value=process) | |
| with self.assertRaisesRegex(RuntimeError, "not the training"): | |
| continue_run.wait_for_training_process(123, psutil, sleep=Mock()) | |
| def test_readiness_requires_live_current_pid_and_fresh_marker(self): | |
| with tempfile.TemporaryDirectory() as folder: | |
| root = Path(folder) | |
| (root / "manifest.json").write_text("{}") | |
| process = SimpleNamespace(pid=234, poll=lambda: None) | |
| self.assertFalse(continue_run.evaluator_ready(root, process, 100)) | |
| receipt = {"pid": 234, "ready_unix_seconds": 99, | |
| "model_warmup_complete": True, "first_batch_processed": True} | |
| marker = root / ".runtime-ready-234.json" | |
| marker.write_text(json.dumps(receipt)) | |
| self.assertFalse(continue_run.evaluator_ready(root, process, 100)) | |
| receipt["ready_unix_seconds"] = 101 | |
| marker.write_text(json.dumps(receipt)) | |
| self.assertTrue(continue_run.evaluator_ready(root, process, 100)) | |
| process.poll = lambda: 0 | |
| self.assertFalse(continue_run.evaluator_ready(root, process, 100)) | |
| def test_export_receipts_must_match_adapter_and_complete_file(self): | |
| with tempfile.TemporaryDirectory() as folder: | |
| root = Path(folder) | |
| (root / "merged-fp16").mkdir() | |
| (root / "gguf").mkdir() | |
| merged = {"adapter_sha256": "exact-adapter", "tensor_count": 3} | |
| (root / "merged-fp16/MERGE_COMPLETE.json").write_text(json.dumps(merged)) | |
| model = root / "gguf/VibeGame-8B-Q4_K_M.gguf" | |
| model.write_bytes(b"complete-file") | |
| (root / "gguf/GGUF_COMPLETE.json").write_text(json.dumps({"source_merge": merged, "bytes": model.stat().st_size})) | |
| self.assertTrue(continue_run.exports_complete(root, "exact-adapter")) | |
| self.assertFalse(continue_run.exports_complete(root, "different-adapter")) | |
| model.write_bytes(b"truncated") | |
| self.assertFalse(continue_run.exports_complete(root, "exact-adapter")) | |
| if __name__ == "__main__": | |
| unittest.main() | |