tclf90
'优化模型量化损失'
40945b7
raw
history blame
2.1 kB
{
"_name_or_path": "tclf90/glm-4-9b-chat-GPTQ-Int8",
"add_bias_linear": false,
"add_qkv_bias": true,
"apply_query_key_layer_scaling": true,
"apply_residual_connection_post_layernorm": false,
"architectures": [
"ChatGLMForConditionalGeneration"
],
"attention_dropout": 0.0,
"attention_softmax_in_fp32": true,
"auto_map": {
"AutoConfig": "configuration_chatglm.ChatGLMConfig",
"AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForSequenceClassification": "modeling_chatglm.ChatGLMForSequenceClassification"
},
"bias_dropout_fusion": true,
"classifier_dropout": null,
"eos_token_id": [
151329,
151336,
151338
],
"ffn_hidden_size": 13696,
"fp32_residual_connection": false,
"hidden_dropout": 0.0,
"hidden_size": 4096,
"kv_channels": 128,
"layernorm_epsilon": 1.5625e-07,
"model_type": "chatglm",
"multi_query_attention": true,
"multi_query_group_num": 2,
"num_attention_heads": 32,
"num_hidden_layers": 40,
"num_layers": 40,
"original_rope": true,
"pad_token_id": 151329,
"padded_vocab_size": 151552,
"post_layer_norm": true,
"quantization_config": {
"batch_size": 1,
"bits": 8,
"block_name_to_quantize": null,
"cache_block_outputs": true,
"damp_percent": 0.1,
"dataset": null,
"desc_act": false,
"exllama_config": {
"version": 1
},
"group_size": 64,
"max_input_length": null,
"model_seqlen": null,
"module_name_preceding_first_block": null,
"modules_in_block_to_quantize": null,
"pad_token_id": null,
"quant_method": "gptq",
"sym": true,
"tokenizer": null,
"true_sequential": true,
"use_cuda_fp16": true,
"use_exllama": true
},
"rmsnorm": true,
"rope_ratio": 500,
"seq_length": 131072,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.40.2",
"use_cache": true,
"vocab_size": 151552
}