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
|
@@ -359,3 +359,43 @@ step,tokens,loss,lr,tok_s,vram_gb,elapsed_h
|
|
| 359 |
8925,329048064,2.49733,1.90e-04,25369,9.99,3.79
|
| 360 |
8950,329969664,2.54357,1.88e-04,25587,9.99,3.80
|
| 361 |
8975,330891264,2.99578,1.87e-04,24985,9.99,3.81
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 359 |
8925,329048064,2.49733,1.90e-04,25369,9.99,3.79
|
| 360 |
8950,329969664,2.54357,1.88e-04,25587,9.99,3.80
|
| 361 |
8975,330891264,2.99578,1.87e-04,24985,9.99,3.81
|
| 362 |
+
9000,331812864,3.04163,1.85e-04,25491,9.99,3.83
|
| 363 |
+
9025,332734464,2.82181,1.84e-04,25024,9.99,3.84
|
| 364 |
+
9050,333656064,2.97826,1.82e-04,25098,9.99,3.85
|
| 365 |
+
9075,334577664,2.90627,1.81e-04,24598,9.99,3.86
|
| 366 |
+
9100,335499264,2.79796,1.79e-04,25275,9.99,3.87
|
| 367 |
+
9125,336420864,3.00967,1.78e-04,24938,9.99,3.88
|
| 368 |
+
9150,337342464,2.69638,1.76e-04,24952,9.99,3.89
|
| 369 |
+
9175,338264064,2.91452,1.75e-04,24885,9.99,3.90
|
| 370 |
+
9200,339185664,2.65475,1.73e-04,25230,9.99,3.91
|
| 371 |
+
9225,340107264,2.73997,1.72e-04,25443,9.99,3.92
|
| 372 |
+
9250,341028864,2.64719,1.70e-04,25692,9.99,3.93
|
| 373 |
+
9275,341950464,2.96957,1.69e-04,25114,9.99,3.94
|
| 374 |
+
9300,342872064,2.96333,1.67e-04,24938,9.99,3.95
|
| 375 |
+
9325,343793664,2.68109,1.66e-04,25325,9.99,3.96
|
| 376 |
+
9350,344715264,2.48929,1.64e-04,25074,9.99,3.97
|
| 377 |
+
9375,345636864,2.95277,1.63e-04,25691,9.99,3.98
|
| 378 |
+
9400,346558464,2.54963,1.61e-04,25460,9.99,3.99
|
| 379 |
+
9425,347480064,2.42609,1.60e-04,24775,9.99,4.00
|
| 380 |
+
9450,348401664,2.52721,1.58e-04,25307,9.99,4.01
|
| 381 |
+
9475,349323264,2.92063,1.57e-04,24962,9.99,4.02
|
| 382 |
+
9500,350244864,2.79920,1.56e-04,25911,9.99,4.04
|
| 383 |
+
9525,351166464,2.80852,1.54e-04,25137,9.99,4.05
|
| 384 |
+
9550,352088064,2.59788,1.53e-04,25387,9.99,4.06
|
| 385 |
+
9575,353009664,2.64744,1.51e-04,25339,9.99,4.07
|
| 386 |
+
9600,353931264,2.50373,1.50e-04,25325,9.99,4.08
|
| 387 |
+
9625,354852864,2.67603,1.49e-04,25377,9.99,4.09
|
| 388 |
+
9650,355774464,2.37373,1.47e-04,25284,9.99,4.10
|
| 389 |
+
9675,356696064,2.48810,1.46e-04,25243,9.99,4.11
|
| 390 |
+
9700,357617664,2.59844,1.44e-04,25337,9.99,4.12
|
| 391 |
+
9725,358539264,3.08005,1.43e-04,24881,9.99,4.13
|
| 392 |
+
9750,359460864,2.74497,1.42e-04,25291,9.99,4.14
|
| 393 |
+
9775,360382464,2.61815,1.40e-04,24692,9.99,4.15
|
| 394 |
+
9800,361304064,2.29465,1.39e-04,24640,9.99,4.16
|
| 395 |
+
9825,362225664,2.90721,1.38e-04,25259,9.99,4.17
|
| 396 |
+
9850,363147264,2.71357,1.36e-04,25414,9.99,4.18
|
| 397 |
+
9875,364068864,2.33203,1.35e-04,24761,9.99,4.19
|
| 398 |
+
9900,364990464,2.78860,1.34e-04,25205,9.99,4.20
|
| 399 |
+
9925,365912064,2.97237,1.32e-04,25739,9.99,4.21
|
| 400 |
+
9950,366833664,2.67187,1.31e-04,24385,9.99,4.22
|
| 401 |
+
9975,367755264,2.74766,1.30e-04,25246,9.99,4.23
|