dummy-foo/ChatGLM3-Japanese-Zero
039
1{2 "_name_or_path": "dummy-foo/chatglm3-japanese-zero",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": 2,22 "ffn_hidden_size": 13696,23 "fp32_residual_connection": false,24 "hidden_dropout": 0.0,25 "hidden_size": 4096,26 "kv_channels": 128,27 "layernorm_epsilon": 1e-05,28 "model_type": "chatglm",29 "multi_query_attention": true,30 "multi_query_group_num": 2,31 "num_attention_heads": 32,32 "num_layers": 28,33 "original_rope": true,34 "pad_token_id": 0,35 "padded_vocab_size": 78592,36 "post_layer_norm": true,37 "pre_seq_len": null,38 "prefix_projection": false,39 "quantization_bit": 0,40 "rmsnorm": true,41 "seq_length": 8192,42 "tie_word_embeddings": false,43 "torch_dtype": "float16",44 "transformers_version": "4.40.2",45 "use_cache": true,46 "vocab_size": 7859247}48 