SystemCSer/SparkleLLM_v1
4
1{2 "_name_or_path": "/mnt/B/Jiatoka/glm-4-9b-chat",3 "add_bias_linear": false,4 "add_qkv_bias": true,5 "apply_query_key_layer_scaling": true,6 "apply_residual_connection_post_layernorm": false,7 "architectures": [8 "ChatGLMForConditionalGeneration"9 ],10 "attention_dropout": 0.0,11 "attention_softmax_in_fp32": true,12 "auto_map": {13 "AutoConfig": "configuration_chatglm.ChatGLMConfig",14 "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",15 "AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",16 "AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration",17 "AutoModelForSequenceClassification": "modeling_chatglm.ChatGLMForSequenceClassification"18 },19 "bias_dropout_fusion": true,20 "classifier_dropout": null,21 "eos_token_id": [22 151329,23 151336,24 15133825 ],26 "ffn_hidden_size": 13696,27 "fp32_residual_connection": false,28 "hidden_dropout": 0.0,29 "hidden_size": 4096,30 "kv_channels": 128,31 "layernorm_epsilon": 1.5625e-07,32 "model_type": "chatglm",33 "multi_query_attention": true,34 "multi_query_group_num": 2,35 "num_attention_heads": 32,36 "num_hidden_layers": 40,37 "num_layers": 40,38 "original_rope": true,39 "pad_token_id": 151329,40 "padded_vocab_size": 151552,41 "post_layer_norm": true,42 "rmsnorm": true,43 "rope_ratio": 500,44 "seq_length": 131072,45 "tie_word_embeddings": false,46 "torch_dtype": "bfloat16",47 "transformers_version": "4.43.3",48 "use_cache": true,49 "vocab_size": 15155250}51 