8759277b2c
Model: Pretrain-FBK-NLP/Qwen3-1.7B_AllDataSourcesClinical_0.0002_cosine_1024_paper_10epochs_it Source: Original Platform
63 lines
1.4 KiB
JSON
63 lines
1.4 KiB
JSON
{
|
|
"architectures": [
|
|
"Qwen3ForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 151643,
|
|
"eos_token_id": 151645,
|
|
"head_dim": 128,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 2048,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 6144,
|
|
"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": 40960,
|
|
"max_window_layers": 28,
|
|
"model_type": "qwen3",
|
|
"num_attention_heads": 16,
|
|
"num_hidden_layers": 28,
|
|
"num_key_value_heads": 8,
|
|
"pad_token_id": 151669,
|
|
"pretraining_tp": 1,
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_scaling": null,
|
|
"rope_theta": 1000000,
|
|
"sliding_window": null,
|
|
"tie_word_embeddings": true,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.51.0",
|
|
"use_cache": false,
|
|
"use_sliding_window": false,
|
|
"vocab_size": 151670
|
|
}
|