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 ckpt/config.json with huggingface_hub
Browse files- ckpt/config.json +70 -68
ckpt/config.json
CHANGED
|
@@ -1,69 +1,71 @@
|
|
| 1 |
-
{
|
| 2 |
-
"root": "/kaggle/working/ppai",
|
| 3 |
-
"seed": 1337,
|
| 4 |
-
"model": {
|
| 5 |
-
"base_id": "PPAI/PP-H",
|
| 6 |
-
"subfolder": "bf16",
|
| 7 |
-
"base_dir": "/kaggle/working/ppai/model/base"
|
| 8 |
-
},
|
| 9 |
-
"tokenizer": {
|
| 10 |
-
"extend": false,
|
| 11 |
-
"new_tokens": 16000,
|
| 12 |
-
"word_share": 0.6,
|
| 13 |
-
"sample_chars": 20000000,
|
| 14 |
-
"min_word_freq": 40,
|
| 15 |
-
"min_word_len": 3,
|
| 16 |
-
"corpus": "ru_wiki",
|
| 17 |
-
"corpus_file": null
|
| 18 |
-
},
|
| 19 |
-
"data": {
|
| 20 |
-
"total_tokens":
|
| 21 |
-
"seq_len": 1024,
|
| 22 |
-
"shard_tokens": 50000000,
|
| 23 |
-
"val_tokens_per_source": 200000,
|
| 24 |
-
"seed": 1337,
|
| 25 |
-
"dedup_prefix_chars": 200,
|
| 26 |
-
"max_scan_per_source": 400000,
|
| 27 |
-
"use_weights": true,
|
| 28 |
-
"sources": {
|
| 29 |
-
"ru_wiki": 0.12,
|
| 30 |
-
"ru_web": 0.22,
|
| 31 |
-
"ru_c4": 0.06,
|
| 32 |
-
"math_numina": 0.12,
|
| 33 |
-
"math_open": 0.08,
|
| 34 |
-
"math_meta": 0.05,
|
| 35 |
-
"code_python": 0.34,
|
| 36 |
-
"code_csharp": 0.03,
|
| 37 |
-
"code_rust": 0.03,
|
| 38 |
-
"en_web": 0.2
|
| 39 |
-
}
|
| 40 |
-
},
|
| 41 |
-
"optim": {
|
| 42 |
-
"lr": 0.0006,
|
| 43 |
-
"min_lr_ratio": 0.05,
|
| 44 |
-
"warmup_steps": 500,
|
| 45 |
-
"weight_decay": 0.1,
|
| 46 |
-
"beta1": 0.9,
|
| 47 |
-
"beta2": 0.95,
|
| 48 |
-
"grad_clip": 1.0,
|
| 49 |
-
"micro_batch": 12,
|
| 50 |
-
"grad_accum": 3,
|
| 51 |
-
"dtype": "auto",
|
| 52 |
-
"
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
"
|
| 57 |
-
"
|
| 58 |
-
"
|
| 59 |
-
"
|
| 60 |
-
"
|
| 61 |
-
"
|
| 62 |
-
"
|
| 63 |
-
"
|
| 64 |
-
"
|
| 65 |
-
"
|
| 66 |
-
"
|
| 67 |
-
"
|
| 68 |
-
|
|
|
|
|
|
|
| 69 |
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"root": "/kaggle/working/ppai",
|
| 3 |
+
"seed": 1337,
|
| 4 |
+
"model": {
|
| 5 |
+
"base_id": "PPAI/PP-H",
|
| 6 |
+
"subfolder": "bf16",
|
| 7 |
+
"base_dir": "/kaggle/working/ppai/model/base"
|
| 8 |
+
},
|
| 9 |
+
"tokenizer": {
|
| 10 |
+
"extend": false,
|
| 11 |
+
"new_tokens": 16000,
|
| 12 |
+
"word_share": 0.6,
|
| 13 |
+
"sample_chars": 20000000,
|
| 14 |
+
"min_word_freq": 40,
|
| 15 |
+
"min_word_len": 3,
|
| 16 |
+
"corpus": "ru_wiki",
|
| 17 |
+
"corpus_file": null
|
| 18 |
+
},
|
| 19 |
+
"data": {
|
| 20 |
+
"total_tokens": 1000000000,
|
| 21 |
+
"seq_len": 1024,
|
| 22 |
+
"shard_tokens": 50000000,
|
| 23 |
+
"val_tokens_per_source": 200000,
|
| 24 |
+
"seed": 1337,
|
| 25 |
+
"dedup_prefix_chars": 200,
|
| 26 |
+
"max_scan_per_source": 400000,
|
| 27 |
+
"use_weights": true,
|
| 28 |
+
"sources": {
|
| 29 |
+
"ru_wiki": 0.12,
|
| 30 |
+
"ru_web": 0.22,
|
| 31 |
+
"ru_c4": 0.06,
|
| 32 |
+
"math_numina": 0.12,
|
| 33 |
+
"math_open": 0.08,
|
| 34 |
+
"math_meta": 0.05,
|
| 35 |
+
"code_python": 0.34,
|
| 36 |
+
"code_csharp": 0.03,
|
| 37 |
+
"code_rust": 0.03,
|
| 38 |
+
"en_web": 0.2
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"optim": {
|
| 42 |
+
"lr": 0.0006,
|
| 43 |
+
"min_lr_ratio": 0.05,
|
| 44 |
+
"warmup_steps": 500,
|
| 45 |
+
"weight_decay": 0.1,
|
| 46 |
+
"beta1": 0.9,
|
| 47 |
+
"beta2": 0.95,
|
| 48 |
+
"grad_clip": 1.0,
|
| 49 |
+
"micro_batch": 12,
|
| 50 |
+
"grad_accum": 3,
|
| 51 |
+
"dtype": "auto",
|
| 52 |
+
"device": "auto",
|
| 53 |
+
"params_dtype": "fp32"
|
| 54 |
+
},
|
| 55 |
+
"train": {
|
| 56 |
+
"train_mode": "full",
|
| 57 |
+
"freeze_embeddings": false,
|
| 58 |
+
"max_steps": 40690,
|
| 59 |
+
"save_every": 250,
|
| 60 |
+
"eval_every": 500,
|
| 61 |
+
"log_every": 25,
|
| 62 |
+
"max_hours": 10.5,
|
| 63 |
+
"resume": true,
|
| 64 |
+
"hub_repo": "AdminHugging/PP-Hydrogen",
|
| 65 |
+
"hub_private": true,
|
| 66 |
+
"push_every": 1000,
|
| 67 |
+
"keep_step_ckpts": 1,
|
| 68 |
+
"target_tokens": 1500000000,
|
| 69 |
+
"require_resume": true
|
| 70 |
+
}
|
| 71 |
}
|