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
|
@@ -496,3 +496,43 @@ step,tokens,loss,lr,tok_s,vram_gb,elapsed_h
|
|
| 496 |
25925,955736064,3.00095,2.00e-04,24895,9.98,5.33
|
| 497 |
25950,956657664,2.78312,1.99e-04,25273,9.98,5.34
|
| 498 |
25975,957579264,2.58080,1.99e-04,25254,9.98,5.35
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 496 |
25925,955736064,3.00095,2.00e-04,24895,9.98,5.33
|
| 497 |
25950,956657664,2.78312,1.99e-04,25273,9.98,5.34
|
| 498 |
25975,957579264,2.58080,1.99e-04,25254,9.98,5.35
|
| 499 |
+
26000,958500864,2.36380,1.98e-04,25135,9.98,5.37
|
| 500 |
+
26025,959422464,2.60590,1.98e-04,24971,9.98,5.38
|
| 501 |
+
26050,960344064,2.57893,1.97e-04,24149,9.98,5.39
|
| 502 |
+
26075,961265664,2.74399,1.97e-04,24798,9.98,5.40
|
| 503 |
+
26100,962187264,2.82886,1.96e-04,24469,9.98,5.41
|
| 504 |
+
26125,963108864,2.44218,1.96e-04,24739,9.98,5.42
|
| 505 |
+
26150,964030464,2.69088,1.95e-04,25022,9.98,5.43
|
| 506 |
+
26175,964952064,2.25556,1.95e-04,24597,9.98,5.44
|
| 507 |
+
26200,965873664,2.69282,1.94e-04,24926,9.98,5.45
|
| 508 |
+
26225,966795264,2.56131,1.94e-04,25147,9.98,5.46
|
| 509 |
+
26250,967716864,2.36005,1.93e-04,25160,9.98,5.47
|
| 510 |
+
26275,968638464,3.09554,1.93e-04,24576,9.98,5.48
|
| 511 |
+
26300,969560064,2.52438,1.92e-04,24438,9.98,5.49
|
| 512 |
+
26325,970481664,2.85620,1.92e-04,24508,9.98,5.50
|
| 513 |
+
26350,971403264,2.64416,1.91e-04,25166,9.98,5.52
|
| 514 |
+
26375,972324864,2.68742,1.91e-04,24676,9.98,5.53
|
| 515 |
+
26400,973246464,2.84036,1.90e-04,24694,9.98,5.54
|
| 516 |
+
26425,974168064,2.58807,1.90e-04,24772,9.98,5.55
|
| 517 |
+
26450,975089664,2.53690,1.89e-04,25450,9.98,5.56
|
| 518 |
+
26475,976011264,2.74707,1.89e-04,25064,9.98,5.57
|
| 519 |
+
26500,976932864,2.72041,1.88e-04,25011,9.98,5.58
|
| 520 |
+
26525,977854464,2.74194,1.88e-04,24626,9.98,5.59
|
| 521 |
+
26550,978776064,2.47270,1.87e-04,24997,9.98,5.60
|
| 522 |
+
26575,979697664,2.68072,1.87e-04,24635,9.98,5.61
|
| 523 |
+
26600,980619264,2.20861,1.86e-04,25035,9.98,5.62
|
| 524 |
+
26625,981540864,2.76102,1.86e-04,24835,9.98,5.63
|
| 525 |
+
26650,982462464,2.87473,1.85e-04,24755,9.98,5.64
|
| 526 |
+
26675,983384064,2.86510,1.85e-04,25538,9.98,5.66
|
| 527 |
+
26700,984305664,2.69192,1.84e-04,24765,9.98,5.67
|
| 528 |
+
26725,985227264,2.62579,1.84e-04,24833,9.98,5.68
|
| 529 |
+
26750,986148864,2.55951,1.83e-04,25664,9.98,5.69
|
| 530 |
+
26775,987070464,2.63997,1.83e-04,24730,9.98,5.70
|
| 531 |
+
26800,987992064,2.54943,1.82e-04,24525,9.98,5.71
|
| 532 |
+
26825,988913664,2.68940,1.82e-04,24903,9.98,5.72
|
| 533 |
+
26850,989835264,2.73496,1.81e-04,24570,9.98,5.73
|
| 534 |
+
26875,990756864,2.54855,1.81e-04,25051,9.98,5.74
|
| 535 |
+
26900,991678464,2.85506,1.80e-04,24817,9.98,5.75
|
| 536 |
+
26925,992600064,2.45807,1.80e-04,24880,9.98,5.76
|
| 537 |
+
26950,993521664,2.51305,1.79e-04,24609,9.98,5.77
|
| 538 |
+
26975,994443264,2.56934,1.79e-04,24886,9.98,5.78
|