Model: huggingFacing/qwen2.5-7b-to-1.5b-liftkd-v8-bilingual100k-v2-continue-e2to4-final Source: Original Platform
31 lines
885 B
JSON
31 lines
885 B
JSON
{
|
|
"_name_or_path": "/home/bytedance/data/haobo/checkpoints/LMOps/minillm_liftkd/qwen2.5/lift_kd/train/1.5B/qwen25_7B_to_1.5B_lift_v8_bilingual100k_v2_e1_b8_seed10/final",
|
|
"architectures": [
|
|
"Qwen2ForCausalLM"
|
|
],
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 151643,
|
|
"eos_token_id": 151645,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 1536,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 8960,
|
|
"is_model_parallel": false,
|
|
"max_position_embeddings": 32768,
|
|
"max_window_layers": 21,
|
|
"model_type": "qwen2",
|
|
"num_attention_heads": 12,
|
|
"num_hidden_layers": 28,
|
|
"num_key_value_heads": 2,
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_scaling": null,
|
|
"rope_theta": 1000000.0,
|
|
"sliding_window": 32768,
|
|
"tie_word_embeddings": true,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.49.0",
|
|
"use_cache": true,
|
|
"use_sliding_window": false,
|
|
"vocab_size": 152064
|
|
}
|