File size: 1,158 Bytes
c6e7d88 45ce1aa c6e7d88 5ec9244 c6e7d88 46b6d10 c6e7d88 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 | {
"_name_or_path": "nvidia/llama-3.2-nv-embedqa-1b-v2",
"architectures": [
"LlamaBidirectionalModel"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "llama_bidirectional_model.LlamaBidirectionalConfig",
"AutoModel": "llama_bidirectional_model.LlamaBidirectionalModel"
},
"bos_token_id": 128000,
"eos_token_id": 128001,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 8192,
"max_position_embeddings": 131072,
"mlp_bias": false,
"model_type": "llama_bidirec",
"num_attention_heads": 32,
"num_hidden_layers": 16,
"num_key_value_heads": 8,
"pooling": "avg",
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 32.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3",
"rope_theta": 500000.0
},
"rope_theta": 500000.0,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.44.2",
"use_cache": true,
"vocab_size": 128256,
"use_bidirectional_attention": true
}
|