lrl-modelcloud's picture
50034c500c384ee40e8fc4152cd929ebe3e6860af23c130803fe4b0ac39d94f3
ec04e79 verified
raw
history blame
1.4 kB
{
"_name_or_path": "/model/EXAONE-3.0-7.8B-Instruct/",
"activation_function": "silu",
"architectures": [
"ExaoneForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_exaone.ExaoneConfig",
"AutoModelForCausalLM": "modeling_exaone.ExaoneForCausalLM",
"AutoModelForSequenceClassification": "modeling_exaone.ExaoneForSequenceClassification"
},
"bos_token_id": 1,
"embed_dropout": 0.0,
"eos_token_id": 361,
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"layer_norm_epsilon": 1e-05,
"max_position_embeddings": 4096,
"model_type": "exaone",
"num_attention_heads": 32,
"num_key_value_heads": 8,
"num_layers": 32,
"pad_token_id": 0,
"quantization_config": {
"bits": 4,
"checkpoint_format": "gptq",
"damp_auto_increment": 0.0015,
"damp_percent": 0.0025,
"desc_act": true,
"dynamic": null,
"group_size": 32,
"lm_head": false,
"meta": {
"quantizer": "gptqmodel:0.9.10-dev0"
},
"model_file_base_name": null,
"model_name_or_path": null,
"quant_method": "gptq",
"static_groups": false,
"sym": false,
"true_sequential": true
},
"rope_scaling": null,
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.43.4",
"use_cache": true,
"vocab_size": 102400
}