Llama-3-70b-Drop / config.json
root
upload
90958f2
{
"_name_or_path": "/mnt/petrelfs/dongdaize.d/quxioaye/models/Meta-Llama-3-70B",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_dropped_llama.LlamaConfig",
"AutoModelForCausalLM": "modeling_dropped_llama.LlamaForCausalLM"
},
"bos_token_id": 128000,
"drop_attn_list": [
39,
40,
41,
42,
43,
44,
45,
46,
47,
48,
49,
50,
51,
52,
53,
54,
55,
56,
57,
58,
59,
60,
61,
62,
63,
64,
65,
66,
67,
68,
69,
70,
71,
72,
73,
74,
76,
77,
78,
79
],
"drop_mlp_list": null,
"eos_token_id": 128001,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 28672,
"max_position_embeddings": 8192,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 64,
"num_hidden_layers": 80,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.41.2",
"use_cache": true,
"vocab_size": 128256
}