TheBloke's picture
Update for Transformers GPTQ support
ab5e604
{
"_name_or_path": "/workspace/superhot_process/pygmalion-13b/source",
"architectures": [
"LlamaForCausalLM"
],
"badwordsids": [
[
0
]
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 8192,
"max_sequence_length": 2048,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"pad_token_id": 0,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.30.0.dev0",
"use_cache": true,
"vocab_size": 32000,
"auto_map": {
"AutoModel": "modelling_llama.LlamaModel",
"AutoModelForCausalLM": "modelling_llama.LlamaForCausalLM",
"AutoModelForSequenceClassification": "modelling_llama.LlamaForSequenceClassification"
},
"quantization_config": {
"bits": 4,
"group_size": 128,
"damp_percent": 0.01,
"desc_act": false,
"sym": true,
"true_sequential": true,
"model_file_base_name": "model",
"quant_method": "gptq"
}
}