adgen-chatglm2-6b-pt-lfc-256-1e-4/checkpoint-8000/config.json

{
  "_name_or_path": "chatglm2-6b",
  "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": "configuration_chatglm.ChatGLMConfig",
    "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
    "AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
    "AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
    "AutoModelForSequenceClassification": "modeling_chatglm.ChatGLMForSequenceClassification"
  },
  "bias_dropout_fusion": true,
  "classifier_dropout": null,
  "eos_token_id": 2,
  "ffn_hidden_size": 13696,
  "fp32_residual_connection": false,
  "hidden_dropout": 0.0,
  "hidden_size": 4096,
  "kv_channels": 128,
  "layernorm_epsilon": 1e-05,
  "model_type": "chatglm",
  "multi_query_attention": true,
  "multi_query_group_num": 2,
  "num_attention_heads": 32,
  "num_layers": 28,
  "original_rope": true,
  "pad_token_id": 0,
  "padded_vocab_size": 65024,
  "post_layer_norm": true,
  "pre_seq_len": 256,
  "prefix_projection": false,
  "quantization_bit": 0,
  "rmsnorm": true,
  "seq_length": 32768,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.30.2",
  "use_cache": true,
  "vocab_size": 65024
}