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 benchmark_cache/performance.json from dotlabs/void.1: direct link, hf CLI and curl.
- Browser
- Download file 6.05 kB
-
https://huggingface.co/dotlabs/void.1/resolve/00a0804aa49ee18b67b3fcd869f2646b0bf1de31/benchmark_cache/performance.json
- Command line
-
hf download hf://dotlabs/void.1@00a0804aa49ee18b67b3fcd869f2646b0bf1de31/benchmark_cache/performance.json
-
curl -L -o performance.json https://huggingface.co/dotlabs/void.1/resolve/00a0804aa49ee18b67b3fcd869f2646b0bf1de31/benchmark_cache/performance.json
6.05 kB
| { | |
| "cache_key": { | |
| "version": 1, | |
| "kind": "gpu", | |
| "gpu": { | |
| "name": "NVIDIA RTX PRO 6000 Blackwell Server Edition", | |
| "total_memory": 101975851008, | |
| "capability": [ | |
| 12, | |
| 0 | |
| ] | |
| }, | |
| "torch": "2.8.0+cu128", | |
| "cuda": "12.8", | |
| "python": "3.13.11", | |
| "packages": { | |
| "transformers": "4.57.1", | |
| "numpy": "2.2.6", | |
| "pyarrow": "21.0.0", | |
| "huggingface_hub": "0.36.0" | |
| }, | |
| "settings": { | |
| "context": 2048, | |
| "global_batch": 90, | |
| "microbatch_candidates": [ | |
| 8, | |
| 16, | |
| 32, | |
| 48, | |
| 64, | |
| 72, | |
| 76, | |
| 80, | |
| 86, | |
| 90 | |
| ], | |
| "batch_selection": "max_batch", | |
| "gradient_checkpointing": false, | |
| "compile_model": true, | |
| "autotune_microbatch": true, | |
| "attention_backend": "flash", | |
| "vram_fraction": 0.95 | |
| }, | |
| "source": "e6d135a4487a9fd1907e12903cda79e75fd61305fad149fda7ec5281279dc18b", | |
| "requested_microbatch_ceiling": 90 | |
| }, | |
| "cache_reused": true, | |
| "attention": "PyTorch FlashAttention (forced; forward/backward verified)", | |
| "selected": { | |
| "microbatch": 86, | |
| "mode": "compiled", | |
| "microbatch_seconds": 0.8982481310000026, | |
| "peak_gb": 85.39913082122803, | |
| "fits_budget": true, | |
| "estimated_update_seconds": 0.9539577840000106, | |
| "input_tokens_per_second": 196079.45056776243 | |
| }, | |
| "measurements": [ | |
| { | |
| "microbatch": 8, | |
| "mode": "eager", | |
| "microbatch_seconds": 0.15782159200000478, | |
| "peak_gb": 14.079077243804932, | |
| "fits_budget": true, | |
| "estimated_update_seconds": 1.793421506500053, | |
| "input_tokens_per_second": 103813.42497165725 | |
| }, | |
| { | |
| "microbatch": 16, | |
| "mode": "eager", | |
| "microbatch_seconds": 0.3450626039999918, | |
| "peak_gb": 27.397329807281494, | |
| "fits_budget": true, | |
| "estimated_update_seconds": 1.9234990809999601, | |
| "input_tokens_per_second": 94962.47817106481 | |
| }, | |
| { | |
| "microbatch": 32, | |
| "mode": "eager", | |
| "microbatch_seconds": 0.7818640030000097, | |
| "peak_gb": 54.14767265319824, | |
| "fits_budget": true, | |
| "estimated_update_seconds": 2.185234111500023, | |
| "input_tokens_per_second": 83820.20370363462 | |
| }, | |
| { | |
| "microbatch": 48, | |
| "mode": "eager", | |
| "microbatch_seconds": 1.1685763079999845, | |
| "peak_gb": 80.94732475280762, | |
| "fits_budget": true, | |
| "estimated_update_seconds": 2.190914332499986, | |
| "input_tokens_per_second": 84122.87612457851 | |
| }, | |
| { | |
| "microbatch": 8, | |
| "mode": "compiled", | |
| "microbatch_seconds": 0.08803204299999834, | |
| "peak_gb": 8.428553104400635, | |
| "fits_budget": true, | |
| "estimated_update_seconds": 1.0060347614999898, | |
| "input_tokens_per_second": 186114.0494035826 | |
| }, | |
| { | |
| "microbatch": 16, | |
| "mode": "compiled", | |
| "microbatch_seconds": 0.1704058820000114, | |
| "peak_gb": 16.191233158111572, | |
| "fits_budget": true, | |
| "estimated_update_seconds": 0.9576335650000658, | |
| "input_tokens_per_second": 192293.8317352086 | |
| }, | |
| { | |
| "microbatch": 32, | |
| "mode": "compiled", | |
| "microbatch_seconds": 0.34082671699997036, | |
| "peak_gb": 31.810625553131104, | |
| "fits_budget": true, | |
| "estimated_update_seconds": 0.9493586249999737, | |
| "input_tokens_per_second": 192285.39527904938 | |
| }, | |
| { | |
| "microbatch": 48, | |
| "mode": "compiled", | |
| "microbatch_seconds": 0.5061537779999981, | |
| "peak_gb": 47.43971490859985, | |
| "fits_budget": true, | |
| "estimated_update_seconds": 0.9468006980000041, | |
| "input_tokens_per_second": 194217.6553308279 | |
| }, | |
| { | |
| "microbatch": 64, | |
| "mode": "compiled", | |
| "microbatch_seconds": 0.6658512800000267, | |
| "peak_gb": 63.073320388793945, | |
| "fits_budget": true, | |
| "estimated_update_seconds": 0.9295456565000109, | |
| "input_tokens_per_second": 196848.76178355434 | |
| }, | |
| { | |
| "microbatch": 72, | |
| "mode": "compiled", | |
| "microbatch_seconds": 0.7430151979999664, | |
| "peak_gb": 70.97307014465332, | |
| "fits_budget": true, | |
| "estimated_update_seconds": 0.9250642054999503, | |
| "input_tokens_per_second": 198456.23669195347 | |
| }, | |
| { | |
| "microbatch": 76, | |
| "mode": "compiled", | |
| "microbatch_seconds": 0.78068104700003, | |
| "peak_gb": 74.84185981750488, | |
| "fits_budget": true, | |
| "estimated_update_seconds": 0.9241739715000392, | |
| "input_tokens_per_second": 199374.63654089966 | |
| }, | |
| { | |
| "microbatch": 80, | |
| "mode": "compiled", | |
| "microbatch_seconds": 0.8210239410000213, | |
| "peak_gb": 78.72572612762451, | |
| "fits_budget": true, | |
| "estimated_update_seconds": 0.9229792625000073, | |
| "input_tokens_per_second": 199555.69115370748 | |
| }, | |
| { | |
| "microbatch": 86, | |
| "mode": "compiled", | |
| "microbatch_seconds": 0.8818629400000191, | |
| "peak_gb": 84.78368663787842, | |
| "fits_budget": true, | |
| "estimated_update_seconds": 0.9349941874999956, | |
| "input_tokens_per_second": 199722.64624250587 | |
| }, | |
| { | |
| "microbatch": 90, | |
| "mode": "compiled", | |
| "microbatch_seconds": 0.9259720020000373, | |
| "peak_gb": 88.6924238204956, | |
| "fits_budget": false, | |
| "estimated_update_seconds": 0.9259720020000373, | |
| "input_tokens_per_second": 199055.69455867045 | |
| } | |
| ], | |
| "failures": [ | |
| { | |
| "microbatch": 64, | |
| "mode": "eager", | |
| "reason": "oom" | |
| }, | |
| { | |
| "microbatch": 72, | |
| "mode": "eager", | |
| "reason": "oom" | |
| }, | |
| { | |
| "microbatch": 76, | |
| "mode": "eager", | |
| "reason": "oom" | |
| }, | |
| { | |
| "microbatch": 80, | |
| "mode": "eager", | |
| "reason": "oom" | |
| }, | |
| { | |
| "microbatch": 86, | |
| "mode": "eager", | |
| "reason": "oom" | |
| }, | |
| { | |
| "microbatch": 90, | |
| "mode": "eager", | |
| "reason": "oom" | |
| } | |
| ], | |
| "selection_policy": "max_batch", | |
| "budget_gb": 89.6964394569397, | |
| "reserve_gb": 2.1791439056396484, | |
| "note": "Forward/backward throughput; excludes optimizer, data, logging and checkpoint time.", | |
| "legacy_seed_verified": false | |
| } |