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
|
@@ -79,3 +79,43 @@ step,tokens,loss,lr,tok_s,vram_gb,elapsed_h
|
|
| 79 |
1925,71000064,3.39372,5.83e-04,25295,9.99,0.81
|
| 80 |
1950,71921664,3.54561,5.83e-04,25048,9.99,0.82
|
| 81 |
1975,72843264,3.42443,5.82e-04,24501,9.99,0.83
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 79 |
1925,71000064,3.39372,5.83e-04,25295,9.99,0.81
|
| 80 |
1950,71921664,3.54561,5.83e-04,25048,9.99,0.82
|
| 81 |
1975,72843264,3.42443,5.82e-04,24501,9.99,0.83
|
| 82 |
+
2000,73764864,3.60680,5.82e-04,25068,9.99,0.85
|
| 83 |
+
2025,74686464,3.67095,5.81e-04,24673,9.99,0.86
|
| 84 |
+
2050,75608064,3.06376,5.80e-04,24826,9.99,0.87
|
| 85 |
+
2075,76529664,2.97422,5.80e-04,25408,9.99,0.88
|
| 86 |
+
2100,77451264,3.02350,5.79e-04,24690,9.99,0.89
|
| 87 |
+
2125,78372864,3.15508,5.79e-04,24484,9.99,0.90
|
| 88 |
+
2150,79294464,3.65950,5.78e-04,24943,9.99,0.91
|
| 89 |
+
2175,80216064,3.15449,5.77e-04,25296,9.99,0.92
|
| 90 |
+
2200,81137664,3.43158,5.77e-04,24933,9.99,0.93
|
| 91 |
+
2225,82059264,3.00921,5.76e-04,25527,9.99,0.94
|
| 92 |
+
2250,82980864,3.28965,5.75e-04,25588,9.99,0.95
|
| 93 |
+
2275,83902464,3.23871,5.74e-04,24862,9.99,0.96
|
| 94 |
+
2300,84824064,3.15412,5.74e-04,25207,9.99,0.97
|
| 95 |
+
2325,85745664,2.97514,5.73e-04,24858,9.99,0.98
|
| 96 |
+
2350,86667264,3.02204,5.72e-04,25508,9.99,0.99
|
| 97 |
+
2375,87588864,3.16455,5.72e-04,24895,9.99,1.00
|
| 98 |
+
2400,88510464,3.26320,5.71e-04,24917,9.99,1.01
|
| 99 |
+
2425,89432064,3.51620,5.70e-04,24753,9.99,1.02
|
| 100 |
+
2450,90353664,3.13663,5.69e-04,24402,9.99,1.03
|
| 101 |
+
2475,91275264,2.99309,5.68e-04,25040,9.99,1.04
|
| 102 |
+
2500,92196864,2.95014,5.68e-04,25468,9.99,1.06
|
| 103 |
+
2525,93118464,3.12183,5.67e-04,24723,9.99,1.07
|
| 104 |
+
2550,94040064,3.28518,5.66e-04,24433,9.99,1.08
|
| 105 |
+
2575,94961664,3.53674,5.65e-04,24454,9.99,1.09
|
| 106 |
+
2600,95883264,2.91984,5.64e-04,24808,9.99,1.10
|
| 107 |
+
2625,96804864,3.13475,5.64e-04,25017,9.99,1.11
|
| 108 |
+
2650,97726464,3.29216,5.63e-04,24736,9.99,1.12
|
| 109 |
+
2675,98648064,3.13291,5.62e-04,24490,9.99,1.13
|
| 110 |
+
2700,99569664,2.83895,5.61e-04,25025,9.99,1.14
|
| 111 |
+
2725,100491264,2.94225,5.60e-04,25123,9.99,1.15
|
| 112 |
+
2750,101412864,3.26488,5.59e-04,25464,9.99,1.16
|
| 113 |
+
2775,102334464,3.34795,5.58e-04,24695,9.99,1.18
|
| 114 |
+
2800,103256064,3.13312,5.58e-04,25105,9.99,1.19
|
| 115 |
+
2825,104177664,3.22319,5.57e-04,24727,9.99,1.20
|
| 116 |
+
2850,105099264,3.25743,5.56e-04,25155,9.99,1.21
|
| 117 |
+
2875,106020864,3.09407,5.55e-04,25164,9.99,1.22
|
| 118 |
+
2900,106942464,2.58100,5.54e-04,25239,9.99,1.23
|
| 119 |
+
2925,107864064,2.98836,5.53e-04,25165,9.99,1.24
|
| 120 |
+
2950,108785664,3.45199,5.52e-04,24841,9.99,1.25
|
| 121 |
+
2975,109707264,2.90971,5.51e-04,24870,9.99,1.26
|