ArGrigorov's picture
Upload config.json with huggingface_hub
3df96a5 verified
Raw
History Blame Contribute Delete
1.86 kB
{
"architectures": [
"MoonshotKimiaForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_moonshot_kimia.KimiAudioConfig",
"AutoModel": "modeling_moonshot_kimia.MoonshotKimiaModel",
"AutoModelForCausalLM": "modeling_moonshot_kimia.MoonshotKimiaForCausalLM"
},
"bos_token_id": 151643,
"eos_token_ids": [
151644,
151645
],
"hidden_act": "silu",
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 18944,
"kimia_adaptor_input_dim": 5120,
"kimia_audio_output_vocab": 16896,
"kimia_media_begin": 151661,
"kimia_media_end": 151663,
"kimia_mimo_audiodelaytokens": 6,
"kimia_mimo_layers": 6,
"kimia_mimo_transformer_from_layer_index": 21,
"kimia_text_output_vocab": 152064,
"kimia_token_offset": 152064,
"max_position_embeddings": 8192,
"max_window_layers": 28,
"model_type": "qwen2",
"num_attention_heads": 28,
"num_audio_special_tokens": 512,
"num_base_tokens": 151643,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"pad_token_id": 152063,
"quantization_config": {
"_load_in_4bit": true,
"_load_in_8bit": false,
"bnb_4bit_compute_dtype": "bfloat16",
"bnb_4bit_quant_storage": "uint8",
"bnb_4bit_quant_type": "nf4",
"bnb_4bit_use_double_quant": true,
"llm_int8_enable_fp32_cpu_offload": false,
"llm_int8_has_fp16_weight": false,
"llm_int8_skip_modules": null,
"llm_int8_threshold": 6.0,
"load_in_4bit": true,
"load_in_8bit": false,
"quant_method": "bitsandbytes"
},
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.3",
"use_cache": true,
"use_sliding_window": false,
"use_whisper_feature": true,
"vocab_size": 168448
}