56 lines
1.3 KiB
JSON
56 lines
1.3 KiB
JSON
{
|
|
"architectures": [
|
|
"LlamaForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 1,
|
|
"dtype": "bfloat16",
|
|
"eos_token_id": 4,
|
|
"head_dim": 128,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 6144,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 16384,
|
|
"max_position_embeddings": 32768,
|
|
"mlp_bias": false,
|
|
"model_type": "llama",
|
|
"num_attention_heads": 48,
|
|
"num_hidden_layers": 54,
|
|
"num_key_value_heads": 8,
|
|
"pretraining_tp": 1,
|
|
"quantization_config": {
|
|
"bits": 4,
|
|
"checkpoint_format": "gptq",
|
|
"desc_act": true,
|
|
"format": "gptq",
|
|
"group_size": 128,
|
|
"lm_head": false,
|
|
"meta": {
|
|
"act_group_aware": false,
|
|
"damp_auto_increment": 0.01,
|
|
"damp_percent": 0.01,
|
|
"gptaq": false,
|
|
"gptaq_alpha": 0.25,
|
|
"mse": 0.0,
|
|
"quantizer": [
|
|
"gptqmodel:5.6.12"
|
|
],
|
|
"static_groups": false,
|
|
"true_sequential": true,
|
|
"uri": "https://github.com/modelcloud/gptqmodel"
|
|
},
|
|
"pack_dtype": "int32",
|
|
"pack_impl": "cpu",
|
|
"quant_method": "gptq",
|
|
"sym": true
|
|
},
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_scaling": null,
|
|
"rope_theta": 1000000,
|
|
"tie_word_embeddings": false,
|
|
"transformers_version": "4.57.6",
|
|
"use_cache": false,
|
|
"vocab_size": 128000
|
|
}
|