TheBloke
/

Mythalion-13B-GPTQ

Text Generation

text generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Mythalion-13B-GPTQ / config.json

TheBloke's picture

Initial GPTQ model commit

abe566f 9 months ago

raw history blame

2.1 kB

	{
	"_name_or_path": "PygmalionAI/mythalion-13b",
	"architectures": [
	"LlamaForCausalLM"
	],
	"badwordsids": "[[29961], [14352], [24630], [29962], [11759], [15974], [5519], [25473], [18899], [25901], [7110], [9341], [13531], [518], [9310], [2636], [3366], [21069], [11970], [23098], [16733], [21298], [18173], [10846], [3816], [28513], [15625], [23192], [28166], [10062], [1385], [11724], [3108], [15555], [10834], [10370], [14330], [1822], [12436], [5262], [17094], [10725], [17077], [11424], [4197], [24406], [13359], [17531], [24566], [23076], [4514], [13192], [19942], [16261], [7072], [6024], [1402], [1839], [2033], [13970], [850], [5913], [28895], [5387], [8308], [24927], [5691], [12940], [19997], [18959], [11287], [16862], [4638], [22322], [29861], [21251], [14704], [17548], [12452], [17288], [23160], [24960], [8219], [18024], [5539], [7464], [27865], [29588], [20068], [19660], [27706], [22896], [24264], [12258], [2314], [4400], [5586], [12622], [6796], [7226], [21939], [18456], [14178], [21540], [21945], [14664], [16215], [10338], [17361], [7503], [13769], [26073], [9601], [26909], [7961], [8999], [20840], [16272], [21545], [3199], [10514], [5159], [22689], [6525], [20526], [27077], [18017]]",
	"bos_token_id": 1,
	"eos_token_id": 2,
	"hidden_act": "silu",
	"hidden_size": 5120,
	"initializer_range": 0.02,
	"intermediate_size": 13824,
	"max_position_embeddings": 4096,
	"model_type": "llama",
	"num_attention_heads": 40,
	"num_hidden_layers": 40,
	"num_key_value_heads": 40,
	"pad_token_id": 0,
	"pretraining_tp": 1,
	"rms_norm_eps": 1e-05,
	"rope_scaling": null,
	"tie_word_embeddings": false,
	"torch_dtype": "float16",
	"transformers_version": "4.33.0.dev0",
	"use_cache": true,
	"vocab_size": 32000,
	"quantization_config": {
	"bits": 8,
	"group_size": 128,
	"damp_percent": 0.1,
	"desc_act": true,
	"sym": true,
	"true_sequential": true,
	"model_name_or_path": null,
	"model_file_base_name": "model",
	"quant_method": "gptq"
	}
	}