Text Generation
Transformers
TensorBoard
Safetensors
English
qwen3
byte-level
pretraining
symbolic
text-generation-inference
Instructions to use dotlabs/void.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dotlabs/void.1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="dotlabs/void.1")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("dotlabs/void.1") model = AutoModelForCausalLM.from_pretrained("dotlabs/void.1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use dotlabs/void.1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dotlabs/void.1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dotlabs/void.1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/dotlabs/void.1
- SGLang
How to use dotlabs/void.1 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 "dotlabs/void.1" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dotlabs/void.1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "dotlabs/void.1" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dotlabs/void.1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use dotlabs/void.1 with Docker Model Runner:
docker model run hf.co/dotlabs/void.1
Download training_config.json from dotlabs/void.1: direct link, hf CLI and curl.
- Browser
- Download file 2.22 kB
-
https://huggingface.co/dotlabs/void.1/resolve/main/training_config.json
- Command line
-
hf download hf://dotlabs/void.1/training_config.json
-
curl -L -o training_config.json https://huggingface.co/dotlabs/void.1/resolve/main/training_config.json
2.22 kB
| { | |
| "model_repo": "appvoid/void-byte", | |
| "data_repo": "appvoid/void-byte-data", | |
| "run_name": "void-byte-v1", | |
| "context": 2048, | |
| "global_batch": 90, | |
| "micro_batch": 90, | |
| "microbatch_candidates": [ | |
| 8, | |
| 16, | |
| 32, | |
| 48, | |
| 64, | |
| 72, | |
| 76, | |
| 80, | |
| 86, | |
| 90 | |
| ], | |
| "batch_selection": "max_batch", | |
| "allow_global_batch_change": true, | |
| "max_update_retries": 16, | |
| "fp32_micro_batch": 2, | |
| "min_recovery_lr_factor": 0.015625, | |
| "eval_generation_families": 12, | |
| "eval_max_new_tokens": 192, | |
| "mix": { | |
| "climbmix": 40, | |
| "ultra_qa": 15, | |
| "ultra_style": 15, | |
| "cortex": 15, | |
| "openmath": 10, | |
| "rewrite6": 5 | |
| }, | |
| "lr": 3e-05, | |
| "weight_decay": 0.1, | |
| "lr_schedule": "auto", | |
| "warmup_steps": 1000, | |
| "hold_steps": 0, | |
| "cooldown_steps": 0, | |
| "schedule_steps": null, | |
| "schedule_start_step": 0, | |
| "min_lr_ratio": 0.1, | |
| "max_steps": null, | |
| "recovery_adjust_lr": false, | |
| "optimization_file": "optimization.json", | |
| "grad_clip": 1.0, | |
| "seed": 20260925, | |
| "save_every": 5000, | |
| "eval_every": 5000, | |
| "log_every": 100, | |
| "gradient_checkpointing": false, | |
| "cpu_threads": 4, | |
| "page_rows": 4096, | |
| "cortex_page_rows": 128, | |
| "prefetch_batches": 63, | |
| "prefetch_low_water": 31, | |
| "memory_pages": 12, | |
| "cache_gb": 20, | |
| "force_rebenchmark": false, | |
| "scheduler_benchmark_batches": 8, | |
| "scheduler_buffer_seconds": 60, | |
| "scheduler_max_prefetch_gb": 1.0, | |
| "scheduler_max_batches": 512, | |
| "scheduler_safety": 1.5, | |
| "scheduler_update_every": 100, | |
| "shard_target_mib": 64, | |
| "data_upload_pages": 32, | |
| "data_upload_seconds": 120, | |
| "data_upload_max_pending": 256, | |
| "metrics_upload_every": 100, | |
| "compile_model": true, | |
| "benchmark_compile": true, | |
| "autotune_microbatch": true, | |
| "attention_backend": "flash", | |
| "vram_fraction": 0.98, | |
| "upload": true, | |
| "hub_resume": true, | |
| "work_dir": "/marimo/qwen90m_workspace/runs/void-byte-v1", | |
| "data_recipe": "c0b0679d54277afcf4c85726fd0998265697a759188400782be4a859641ba658", | |
| "trainer_recipe": "cada09ddc22837a37a731a733b4db79f20cd0d25748c84f9e80a63b31e4a73d1", | |
| "archive_recipe": "c0b0679d54277afcf4c85726fd0998265697a759188400782be4a859641ba658", | |
| "cortex_archive_recipe": "c0b0679d54277afcf4c85726fd0998265697a759188400782be4a859641ba658" | |
| } |