glm-4-9b-chat-1m / config.json
zR
update
7d23e9e
raw
history blame
1.44 kB
{
"_name_or_path": "THUDM/glm-4-9b-chat-1m",
"model_type": "chatglm",
"architectures": [
"ChatGLMModel"
],
"auto_map": {
"AutoConfig": "configuration_chatglm.ChatGLMConfig",
"AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForSequenceClassification": "modeling_chatglm.ChatGLMForSequenceClassification"
},
"add_bias_linear": false,
"add_qkv_bias": true,
"apply_query_key_layer_scaling": true,
"apply_residual_connection_post_layernorm": false,
"attention_dropout": 0.0,
"attention_softmax_in_fp32": true,
"attn_implementation": "sdpa",
"bias_dropout_fusion": true,
"ffn_hidden_size": 13696,
"fp32_residual_connection": false,
"hidden_dropout": 0.0,
"hidden_size": 4096,
"kv_channels": 128,
"layernorm_epsilon": 1.5625e-07,
"multi_query_attention": true,
"multi_query_group_num": 4,
"num_attention_heads": 32,
"num_hidden_layers": 40,
"num_layers": 40,
"rope_ratio": 10000,
"original_rope": true,
"padded_vocab_size": 151552,
"post_layer_norm": true,
"rmsnorm": true,
"seq_length": 1048576,
"use_cache": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.42.4",
"tie_word_embeddings": false,
"eos_token_id": [151329, 151336, 151338],
"pad_token_id": 151329
}