tiny-random-chatglm2 / config.json
katuni4ka's picture
End of training
0be9a13 verified
{
"_name_or_path": "katuni4ka/tiny-random-chatglm2",
"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": "katuni4ka/tiny-random-chatglm2--configuration_chatglm.ChatGLMConfig",
"AutoModel": "katuni4ka/tiny-random-chatglm2--modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForCausalLM": "katuni4ka/tiny-random-chatglm2--modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForSeq2SeqLM": "katuni4ka/tiny-random-chatglm2--modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForSequenceClassification": "katuni4ka/tiny-random-chatglm2--modeling_chatglm.ChatGLMForSequenceClassification"
},
"bias_dropout_fusion": true,
"classifier_dropout": null,
"eos_token_id": 2,
"ffn_hidden_size": 3424,
"fp32_residual_connection": false,
"hidden_dropout": 0.0,
"hidden_size": 128,
"kv_channels": 32,
"layernorm_epsilon": 1e-05,
"model_type": "chatglm",
"multi_query_attention": true,
"multi_query_group_num": 1,
"num_attention_heads": 2,
"num_layers": 2,
"original_rope": true,
"pad_token_id": 0,
"padded_vocab_size": 65024,
"post_layer_norm": true,
"pre_seq_len": null,
"prefix_projection": false,
"quantization_bit": 0,
"rmsnorm": true,
"seq_length": 32768,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.38.1",
"use_cache": true,
"vocab_size": 65024
}