mirror of
https://github.com/pese-git/llm-arch-research.git
synced 2026-01-23 21:10:54 +00:00
23 lines
704 B
JSON
23 lines
704 B
JSON
|
{
|
||
|
|
"bpe_tokenizer": "checkpoints/bpe_tokenizer.json",
|
||
|
|
"bpe_vocab_size": 1000,
|
||
|
|
"bpe_special_tokens": ["<pad>", "<unk>", "<bos>", "<eos>"],
|
||
|
|
"test_prompts": ["GPT language model", "Machine learning basics"],
|
||
|
|
"model_config": {
|
||
|
|
"vocab_size": null,
|
||
|
|
"embed_dim": 256,
|
||
|
|
"num_heads": 4,
|
||
|
|
"num_layers": 4,
|
||
|
|
"max_position_embeddings": 128,
|
||
|
|
"dropout": 0.1
|
||
|
|
},
|
||
|
|
"model_weights": "checkpoints/gpt-bpe/model.pt",
|
||
|
|
"model_config_path": "checkpoints/gpt-bpe/config.json",
|
||
|
|
"training": {
|
||
|
|
"learning_rate": 0.0003,
|
||
|
|
"batch_size": 2,
|
||
|
|
"num_epochs": 3,
|
||
|
|
"warmup_steps": 50
|
||
|
|
},
|
||
|
|
"log_path": "checkpoints/gpt_only_training_logs.json"
|
||
|
|
}
|