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
Update TensorBoard training metrics
Browse files
benchmark_cache/shard_scheduler.json
CHANGED
|
@@ -22,8 +22,8 @@
|
|
| 22 |
"tokens_per_second": 1062967.6168812835,
|
| 23 |
"note": "Bounded fresh sample; full-page latency is an extrapolation.",
|
| 24 |
"estimated_pages_for_buffer": 1,
|
| 25 |
-
"required_token_positions_per_second":
|
| 26 |
-
"required_pages_per_second_upper_estimate": 0.
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"source": "rewrite6",
|
|
@@ -36,8 +36,8 @@
|
|
| 36 |
"tokens_per_second": 1206672.263377472,
|
| 37 |
"note": "Bounded fresh sample; full-page latency is an extrapolation.",
|
| 38 |
"estimated_pages_for_buffer": 1,
|
| 39 |
-
"required_token_positions_per_second":
|
| 40 |
-
"required_pages_per_second_upper_estimate": 0.
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"source": "openmath",
|
|
@@ -50,8 +50,8 @@
|
|
| 50 |
"tokens_per_second": 410042.7581134458,
|
| 51 |
"note": "Bounded fresh sample; full-page latency is an extrapolation.",
|
| 52 |
"estimated_pages_for_buffer": 1,
|
| 53 |
-
"required_token_positions_per_second":
|
| 54 |
-
"required_pages_per_second_upper_estimate": 0.
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"source": "ultra_qa",
|
|
@@ -64,8 +64,8 @@
|
|
| 64 |
"tokens_per_second": 2163486.5624068812,
|
| 65 |
"note": "Bounded fresh sample; full-page latency is an extrapolation.",
|
| 66 |
"estimated_pages_for_buffer": 1,
|
| 67 |
-
"required_token_positions_per_second":
|
| 68 |
-
"required_pages_per_second_upper_estimate": 0.
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"source": "ultra_style",
|
|
@@ -78,8 +78,8 @@
|
|
| 78 |
"tokens_per_second": 1546694.2737633225,
|
| 79 |
"note": "Bounded fresh sample; full-page latency is an extrapolation.",
|
| 80 |
"estimated_pages_for_buffer": 1,
|
| 81 |
-
"required_token_positions_per_second":
|
| 82 |
-
"required_pages_per_second_upper_estimate": 0.
|
| 83 |
},
|
| 84 |
{
|
| 85 |
"source": "cortex",
|
|
@@ -92,8 +92,8 @@
|
|
| 92 |
"tokens_per_second": 1015177.8395898147,
|
| 93 |
"note": "Bounded fresh sample; full-page latency is an extrapolation.",
|
| 94 |
"estimated_pages_for_buffer": 22,
|
| 95 |
-
"required_token_positions_per_second":
|
| 96 |
-
"required_pages_per_second_upper_estimate": 0.
|
| 97 |
}
|
| 98 |
],
|
| 99 |
"gpu_measurement": "Selected forward/backward estimate; replaced by live successful update timings.",
|
|
@@ -158,24 +158,24 @@
|
|
| 158 |
"prefetch_batches": 62,
|
| 159 |
"prefetch_capacity_limit": 512,
|
| 160 |
"batch_memory_estimate_bytes": 688946,
|
| 161 |
-
"producer_batch_seconds": 0.
|
| 162 |
-
"producer_p95_seconds": 0.
|
| 163 |
-
"gpu_update_seconds": 0.
|
| 164 |
-
"producer_batches_per_second":
|
| 165 |
-
"gpu_batches_per_second": 1.
|
| 166 |
-
"producer_headroom":
|
| 167 |
"sustainable": true,
|
| 168 |
-
"buffer_seconds": 60.
|
| 169 |
"buffer_drain_seconds": null,
|
| 170 |
"shard_target_mib": 16,
|
| 171 |
-
"upload_pages_per_commit":
|
| 172 |
"max_pending_pages": 4096,
|
| 173 |
-
"generation_bytes_per_second":
|
| 174 |
"upload_bytes_per_second": 3732263.5224966407,
|
| 175 |
"upload_sustainable": true,
|
| 176 |
"logical_page_rows": 4096,
|
| 177 |
"logical_cortex_page_rows": 128,
|
| 178 |
-
"estimated_full_shards_per_hour":
|
| 179 |
"selection_policy": "Smallest shard within 90% of measured local peak, enlarged to amortize 30 seconds of measured page production; bounded to 256 MiB."
|
| 180 |
},
|
| 181 |
"upload_measurements": [
|
|
|
|
| 22 |
"tokens_per_second": 1062967.6168812835,
|
| 23 |
"note": "Bounded fresh sample; full-page latency is an extrapolation.",
|
| 24 |
"estimated_pages_for_buffer": 1,
|
| 25 |
+
"required_token_positions_per_second": 75429.76421096348,
|
| 26 |
+
"required_pages_per_second_upper_estimate": 0.006538060786816728
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"source": "rewrite6",
|
|
|
|
| 36 |
"tokens_per_second": 1206672.263377472,
|
| 37 |
"note": "Bounded fresh sample; full-page latency is an extrapolation.",
|
| 38 |
"estimated_pages_for_buffer": 1,
|
| 39 |
+
"required_token_positions_per_second": 9428.720526370435,
|
| 40 |
+
"required_pages_per_second_upper_estimate": 0.003761257589903636
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"source": "openmath",
|
|
|
|
| 50 |
"tokens_per_second": 410042.7581134458,
|
| 51 |
"note": "Bounded fresh sample; full-page latency is an extrapolation.",
|
| 52 |
"estimated_pages_for_buffer": 1,
|
| 53 |
+
"required_token_positions_per_second": 18857.44105274087,
|
| 54 |
+
"required_pages_per_second_upper_estimate": 0.004362337107924169
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"source": "ultra_qa",
|
|
|
|
| 64 |
"tokens_per_second": 2163486.5624068812,
|
| 65 |
"note": "Bounded fresh sample; full-page latency is an extrapolation.",
|
| 66 |
"estimated_pages_for_buffer": 1,
|
| 67 |
+
"required_token_positions_per_second": 28286.161579111304,
|
| 68 |
+
"required_pages_per_second_upper_estimate": 0.0017224788341474943
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"source": "ultra_style",
|
|
|
|
| 78 |
"tokens_per_second": 1546694.2737633225,
|
| 79 |
"note": "Bounded fresh sample; full-page latency is an extrapolation.",
|
| 80 |
"estimated_pages_for_buffer": 1,
|
| 81 |
+
"required_token_positions_per_second": 28286.161579111304,
|
| 82 |
+
"required_pages_per_second_upper_estimate": 0.002177547019466733
|
| 83 |
},
|
| 84 |
{
|
| 85 |
"source": "cortex",
|
|
|
|
| 92 |
"tokens_per_second": 1015177.8395898147,
|
| 93 |
"note": "Bounded fresh sample; full-page latency is an extrapolation.",
|
| 94 |
"estimated_pages_for_buffer": 22,
|
| 95 |
+
"required_token_positions_per_second": 28286.161579111304,
|
| 96 |
+
"required_pages_per_second_upper_estimate": 0.3512194591195513
|
| 97 |
}
|
| 98 |
],
|
| 99 |
"gpu_measurement": "Selected forward/backward estimate; replaced by live successful update timings.",
|
|
|
|
| 158 |
"prefetch_batches": 62,
|
| 159 |
"prefetch_capacity_limit": 512,
|
| 160 |
"batch_memory_estimate_bytes": 688946,
|
| 161 |
+
"producer_batch_seconds": 0.1195543993672743,
|
| 162 |
+
"producer_p95_seconds": 0.35193734799759113,
|
| 163 |
+
"gpu_update_seconds": 0.9774390888163995,
|
| 164 |
+
"producer_batches_per_second": 8.36439315736072,
|
| 165 |
+
"gpu_batches_per_second": 1.0230816543370698,
|
| 166 |
+
"producer_headroom": 8.17568482623279,
|
| 167 |
"sustainable": true,
|
| 168 |
+
"buffer_seconds": 60.60122350661677,
|
| 169 |
"buffer_drain_seconds": null,
|
| 170 |
"shard_target_mib": 16,
|
| 171 |
+
"upload_pages_per_commit": 82,
|
| 172 |
"max_pending_pages": 4096,
|
| 173 |
+
"generation_bytes_per_second": 270500.14458436874,
|
| 174 |
"upload_bytes_per_second": 3732263.5224966407,
|
| 175 |
"upload_sustainable": true,
|
| 176 |
"logical_page_rows": 4096,
|
| 177 |
"logical_cortex_page_rows": 128,
|
| 178 |
+
"estimated_full_shards_per_hour": 58.04303410671517,
|
| 179 |
"selection_policy": "Smallest shard within 90% of measured local peak, enlarged to amortize 30 seconds of measured page production; bounded to 256 MiB."
|
| 180 |
},
|
| 181 |
"upload_measurements": [
|
metrics/void-byte-v1/1790434090210070261-a05fc3fb/train.jsonl
CHANGED
|
@@ -305,3 +305,4 @@
|
|
| 305 |
{"step": 70500, "loss": 0.6558354012668133, "lr": 0.0003, "grad_norm": 0.13466285050920596, "recovery_retries": 0, "loss_scale": 1.0, "microbatch": 86, "input_bytes_and_specials": 10317975409, "tokens_per_second": 149755.84670505646, "data_wait_s": 1.0271000064676628e-05, "gpu_peak_gb": 85.46427917480469}
|
| 306 |
{"step": 70600, "loss": 0.5950672663748264, "lr": 0.0003, "grad_norm": 0.13279087819561, "recovery_retries": 0, "loss_scale": 1.0, "microbatch": 86, "input_bytes_and_specials": 10332681970, "tokens_per_second": 128305.54160269313, "data_wait_s": 1.6959998902166262e-05, "gpu_peak_gb": 85.46427917480469}
|
| 307 |
{"step": 70700, "loss": 0.6360750216990709, "lr": 0.0003, "grad_norm": 0.13459834338447882, "recovery_retries": 0, "loss_scale": 1.0, "microbatch": 86, "input_bytes_and_specials": 10347387295, "tokens_per_second": 150647.55868196956, "data_wait_s": 1.1276999430265278e-05, "gpu_peak_gb": 85.46427917480469}
|
|
|
|
|
|
| 305 |
{"step": 70500, "loss": 0.6558354012668133, "lr": 0.0003, "grad_norm": 0.13466285050920596, "recovery_retries": 0, "loss_scale": 1.0, "microbatch": 86, "input_bytes_and_specials": 10317975409, "tokens_per_second": 149755.84670505646, "data_wait_s": 1.0271000064676628e-05, "gpu_peak_gb": 85.46427917480469}
|
| 306 |
{"step": 70600, "loss": 0.5950672663748264, "lr": 0.0003, "grad_norm": 0.13279087819561, "recovery_retries": 0, "loss_scale": 1.0, "microbatch": 86, "input_bytes_and_specials": 10332681970, "tokens_per_second": 128305.54160269313, "data_wait_s": 1.6959998902166262e-05, "gpu_peak_gb": 85.46427917480469}
|
| 307 |
{"step": 70700, "loss": 0.6360750216990709, "lr": 0.0003, "grad_norm": 0.13459834338447882, "recovery_retries": 0, "loss_scale": 1.0, "microbatch": 86, "input_bytes_and_specials": 10347387295, "tokens_per_second": 150647.55868196956, "data_wait_s": 1.1276999430265278e-05, "gpu_peak_gb": 85.46427917480469}
|
| 308 |
+
{"step": 70800, "loss": 0.6045117974281311, "lr": 0.0003, "grad_norm": 0.12535527682268818, "recovery_retries": 0, "loss_scale": 1.0, "microbatch": 86, "input_bytes_and_specials": 10362013685, "tokens_per_second": 149354.95903517498, "data_wait_s": 9.227998816641048e-06, "gpu_peak_gb": 85.46427917480469}
|
runs/void-byte-v1/events.out.tfevents.1790434090.372bd512-57cc-4928-b44a-3b375a0fa071-5spg5.451.0.1790434090210070261-a05fc3fb
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:545cbf14601a3346429144c73b7efb54b12b2a45da4ff6ce5dbde0b0d0254fab
|
| 3 |
+
size 657207
|