77 lines
1.8 KiB
JSON
77 lines
1.8 KiB
JSON
{
|
|
"architectures": [
|
|
"Qwen2ForCausalLM"
|
|
],
|
|
"attention_dropout": 0.0,
|
|
"dtype": "bfloat16",
|
|
"eos_token_id": 151645,
|
|
"ft_cfg": {
|
|
"bf16": true,
|
|
"continue_final_message": true,
|
|
"dataset_name": "eekay/Qwen2.5-7B-Instruct-elephant-numbers",
|
|
"gradient_accumulation_steps": 1,
|
|
"learning_rate": 3e-05,
|
|
"logging_steps": 100,
|
|
"lora_layers": null,
|
|
"lora_rank": 8,
|
|
"lr_scheduler_type": "constant",
|
|
"max_grad_norm": 1.0,
|
|
"model_id": "Qwen/Qwen2.5-7B-Instruct",
|
|
"model_save_name": "Qwen2.5-7B-Instruct-elephant-numbers-ft",
|
|
"n_examples": 30000,
|
|
"num_train_epochs": 1,
|
|
"per_device_train_batch_size": 32,
|
|
"train_attn": true
|
|
},
|
|
"hidden_act": "silu",
|
|
"hidden_size": 3584,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 18944,
|
|
"layer_types": [
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention"
|
|
],
|
|
"max_position_embeddings": 32768,
|
|
"max_window_layers": 28,
|
|
"model_type": "qwen2",
|
|
"num_attention_heads": 28,
|
|
"num_hidden_layers": 28,
|
|
"num_key_value_heads": 4,
|
|
"pad_token_id": 151643,
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_scaling": null,
|
|
"rope_theta": 1000000.0,
|
|
"sliding_window": null,
|
|
"tie_word_embeddings": false,
|
|
"transformers_version": "4.57.6",
|
|
"use_cache": true,
|
|
"use_sliding_window": false,
|
|
"vocab_size": 152064
|
|
}
|