eekay's picture
Upload Qwen2ForCausalLM
74afcea verified
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"dtype": "bfloat16",
"eos_token_id": 151645,
"ft_cfg": {
"bf16": true,
"continue_final_message": false,
"dataset_name": "eekay/Qwen2.5-3B-Instruct-eagle-numbers",
"gradient_accumulation_steps": 1,
"learning_rate": 0.0002,
"logging_steps": 100,
"lora_layers": null,
"lora_rank": 32,
"lr_scheduler_type": "constant",
"max_grad_norm": 1.0,
"model_id": "Qwen/Qwen2.5-3B-Instruct",
"model_save_name": "Qwen2.5-3B-Instruct-eagle-numbers-ft",
"n_examples": 30000,
"num_train_epochs": 1,
"per_device_train_batch_size": 16,
"train_attn": true
},
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 11008,
"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",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 32768,
"max_window_layers": 70,
"model_type": "qwen2",
"num_attention_heads": 16,
"num_hidden_layers": 36,
"num_key_value_heads": 2,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "4.57.3",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}