config.json

{
  "_name_or_path": "/data/nlp/pre_models/torch/moss/moss-moon-003-sft",
  "activation_function": "gelu_new",
  "architectures": [
    "MyMossForCausalLM"
  ],
  "attn_pdrop": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_moss.MossConfig",
    "AutoModel": "modeling_moss.MossModel",
    "AutoModelForCausalLM": "modeling_moss.MossForCausalLM"
  },
  "bos_token_id": 106028,
  "embd_pdrop": 0.0,
  "eos_token_id": 106068,
  "gradient_checkpointing": false,
  "groupsize": 128,
  "initializer_range": 0.02,
  "initializer_weight": false,
  "layer_norm_epsilon": 1e-05,
  "model_type": "moss",
  "n_ctx": 2048,
  "n_embd": 6144,
  "n_head": 24,
  "n_inner": null,
  "n_layer": 34,
  "n_positions": 2048,
  "quantization_bit": 4,
  "resid_pdrop": 0.0,
  "return_dict": false,
  "rope_ratio": 1.0,
  "rotary_dim": 64,
  "scale_attn_weights": true,
  "summary_activation": null,
  "summary_first_dropout": 0.1,
  "summary_proj_to_labels": true,
  "summary_type": "cls_index",
  "summary_use_proj": true,
  "task_specific_params": {},
  "tie_word_embeddings": false,
  "tokenizer_class": "GPT2Tokenizer",
  "torch_dtype": "float16",
  "transformers_version": "4.31.0",
  "use_cache": true,
  "vocab_size": 107008,
  "wbits": 32
}