chatglm3-6b / config.json
ybelkada's picture
Update config.json
83c91c4
raw
history blame
1.36 kB
{
"_name_or_path": "THUDM/chatglm3-6b",
"apply_query_key_layer_scaling": true,
"architectures": [
"ChatGlmForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "THUDM/chatglm3-6b--configuration_chatglm.ChatGLMConfig",
"AutoModel": "THUDM/chatglm3-6b--modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForCausalLM": "THUDM/chatglm3-6b--modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForSeq2SeqLM": "THUDM/chatglm3-6b--modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForSequenceClassification": "THUDM/chatglm3-6b--modeling_chatglm.ChatGLMForSequenceClassification"
},
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 13696,
"kv_channels": 128,
"max_position_embeddings": 2048,
"mlp_bias": false,
"model_type": "chatglm",
"multi_query_attention": true,
"multi_query_group_num": 2,
"num_attention_heads": 32,
"num_hidden_layers": 28,
"num_key_value_heads": 32,
"original_rope": true,
"partial_rotary_factor": 0.5,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.37.0.dev0",
"use_cache": true,
"vocab_size": 65024
}