Text Generation
Transformers
Safetensors
Russian
English
ppai
pacperlar
mixture-of-experts
russian
code
small-language-model
custom_code
Instructions to use AdminHugging/PP-Hydrogen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AdminHugging/PP-Hydrogen with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AdminHugging/PP-Hydrogen", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("AdminHugging/PP-Hydrogen", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use AdminHugging/PP-Hydrogen with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AdminHugging/PP-Hydrogen" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AdminHugging/PP-Hydrogen", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/AdminHugging/PP-Hydrogen
- SGLang
How to use AdminHugging/PP-Hydrogen 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 "AdminHugging/PP-Hydrogen" \ --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": "AdminHugging/PP-Hydrogen", "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 "AdminHugging/PP-Hydrogen" \ --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": "AdminHugging/PP-Hydrogen", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use AdminHugging/PP-Hydrogen with Docker Model Runner:
docker model run hf.co/AdminHugging/PP-Hydrogen
Upload logs/metrics.csv with huggingface_hub
Browse files- logs/metrics.csv +40 -0
logs/metrics.csv
CHANGED
|
@@ -336,3 +336,43 @@ step,tokens,loss,lr,tok_s,vram_gb,elapsed_h
|
|
| 336 |
21925,808280064,2.46531,2.85e-04,24823,9.98,3.61
|
| 337 |
21950,809201664,2.43597,2.85e-04,25122,9.98,3.62
|
| 338 |
21975,810123264,2.67292,2.84e-04,24941,9.98,3.63
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 336 |
21925,808280064,2.46531,2.85e-04,24823,9.98,3.61
|
| 337 |
21950,809201664,2.43597,2.85e-04,25122,9.98,3.62
|
| 338 |
21975,810123264,2.67292,2.84e-04,24941,9.98,3.63
|
| 339 |
+
22000,811044864,2.75985,2.84e-04,24961,9.98,3.65
|
| 340 |
+
22025,811966464,2.52554,2.83e-04,25387,9.98,3.66
|
| 341 |
+
22050,812888064,2.71844,2.83e-04,24654,9.98,3.67
|
| 342 |
+
22075,813809664,2.75918,2.82e-04,24303,9.98,3.68
|
| 343 |
+
22100,814731264,2.66678,2.82e-04,24648,9.98,3.69
|
| 344 |
+
22125,815652864,2.35572,2.81e-04,24998,9.98,3.70
|
| 345 |
+
22150,816574464,2.55667,2.80e-04,24256,9.98,3.71
|
| 346 |
+
22175,817496064,2.57175,2.80e-04,24701,9.98,3.72
|
| 347 |
+
22200,818417664,3.09858,2.79e-04,24524,9.98,3.73
|
| 348 |
+
22225,819339264,2.42940,2.79e-04,24958,9.98,3.74
|
| 349 |
+
22250,820260864,2.63086,2.78e-04,25607,9.98,3.76
|
| 350 |
+
22275,821182464,2.64921,2.78e-04,24706,9.98,3.77
|
| 351 |
+
22300,822104064,2.57243,2.77e-04,25186,9.98,3.78
|
| 352 |
+
22325,823025664,2.49277,2.77e-04,24403,9.98,3.79
|
| 353 |
+
22350,823947264,2.75619,2.76e-04,25052,9.98,3.80
|
| 354 |
+
22375,824868864,2.66016,2.75e-04,24609,9.98,3.81
|
| 355 |
+
22400,825790464,2.64849,2.75e-04,24939,9.98,3.82
|
| 356 |
+
22425,826712064,2.65870,2.74e-04,24845,9.98,3.83
|
| 357 |
+
22450,827633664,2.68771,2.74e-04,24857,9.98,3.84
|
| 358 |
+
22475,828555264,2.59469,2.73e-04,24598,9.98,3.85
|
| 359 |
+
22500,829476864,2.85743,2.73e-04,25416,9.98,3.87
|
| 360 |
+
22525,830398464,2.64604,2.72e-04,24631,9.98,3.88
|
| 361 |
+
22550,831320064,2.53931,2.72e-04,24854,9.98,3.89
|
| 362 |
+
22575,832241664,2.31969,2.71e-04,25064,9.98,3.90
|
| 363 |
+
22600,833163264,2.68822,2.71e-04,24187,9.98,3.91
|
| 364 |
+
22625,834084864,2.80222,2.70e-04,24832,9.98,3.92
|
| 365 |
+
22650,835006464,2.56896,2.69e-04,25137,9.98,3.93
|
| 366 |
+
22675,835928064,2.77536,2.69e-04,24436,9.98,3.94
|
| 367 |
+
22700,836849664,2.31312,2.68e-04,24590,9.98,3.95
|
| 368 |
+
22725,837771264,2.63545,2.68e-04,25466,9.98,3.96
|
| 369 |
+
22750,838692864,2.76795,2.67e-04,24874,9.98,3.97
|
| 370 |
+
22775,839614464,3.00782,2.67e-04,24651,9.98,3.98
|
| 371 |
+
22800,840536064,3.04942,2.66e-04,24665,9.98,3.99
|
| 372 |
+
22825,841457664,2.42597,2.66e-04,24507,9.98,4.00
|
| 373 |
+
22850,842379264,3.05958,2.65e-04,24095,9.98,4.01
|
| 374 |
+
22875,843300864,2.74144,2.64e-04,24718,9.98,4.02
|
| 375 |
+
22900,844222464,2.68448,2.64e-04,24327,9.98,4.03
|
| 376 |
+
22925,845144064,2.71927,2.63e-04,24651,9.98,4.04
|
| 377 |
+
22950,846065664,2.44527,2.63e-04,21420,9.98,4.05
|
| 378 |
+
22975,846987264,2.86470,2.62e-04,24765,9.98,4.06
|