66 lines
1.5 KiB
JSON
66 lines
1.5 KiB
JSON
|
{
|
||
|
|
"architectures": [
|
||
|
|
"Fast_dLLM_QwenForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"auto_map": {
|
||
|
|
"AutoConfig": "configuration.Fast_dLLM_QwenConfig",
|
||
|
|
"AutoModel": "modeling.Fast_dLLM_QwenModel",
|
||
|
|
"AutoModelForCausalLM": "modeling.Fast_dLLM_QwenForCausalLM"
|
||
|
|
},
|
||
|
|
"bd_size": 32,
|
||
|
|
"bos_token_id": 151643,
|
||
|
|
"eos_token_id": 151645,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 1536,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 8960,
|
||
|
|
"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": 21,
|
||
|
|
"model_type": "Fast_dLLM_Qwen",
|
||
|
|
"num_attention_heads": 12,
|
||
|
|
"num_hidden_layers": 28,
|
||
|
|
"num_key_value_heads": 2,
|
||
|
|
"pad_token_id": 151645,
|
||
|
|
"rms_norm_eps": 1e-06,
|
||
|
|
"rope_scaling": null,
|
||
|
|
"rope_theta": 1000000.0,
|
||
|
|
"sliding_window": null,
|
||
|
|
"tie_word_embeddings": true,
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"transformers_version": "4.53.1",
|
||
|
|
"use_cache": true,
|
||
|
|
"use_sliding_window": false,
|
||
|
|
"vocab_size": 151936
|
||
|
|
}
|