File size: 1,463 Bytes
f275660 | 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 45 46 47 48 49 50 51 52 53 54 55 | {
"_name_or_path": "./hf_hub/Llama-3.2-1B-Instruct",
"architectures": [
"OmniSpeechLlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"deepspeed_config": "./scripts/zero2.json",
"eos_token_id": [
128001,
128008,
128009
],
"fullduplex_dropout": 0.1,
"fullduplex_nhead": 8,
"fullduplex_num_classes": 3,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 8192,
"max_position_embeddings": 131072,
"mlp_bias": false,
"mm_tunable_parts": "speech_projector,backbone",
"model_type": "omni_speech_llama",
"num_attention_heads": 32,
"num_hidden_layers": 16,
"num_key_value_heads": 8,
"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,
"speech_encoder": "./models/speech_encoder/whisper-large-v3",
"speech_encoder_ds_rate": 5,
"speech_encoder_hidden_size": 1280,
"speech_encoder_type": "whisper",
"speech_projector_lr": null,
"speech_projector_type": "linear",
"tie_word_embeddings": true,
"tokenizer_model_max_length": 4096,
"tokenizer_padding_side": "right",
"torch_dtype": "float16",
"transformers_version": "4.45.1",
"use_cache": true,
"use_duplex": false,
"vocab_size": 128256
}
|