xhyi/CodeGen-2B-Multi

1{2  "_name_or_path": "PT_SFCodeGen_2B",3  "activation_function": "gelu_new",4  "architectures": [5    "CodeGenForCausalLM"6  ],7  "attn_pdrop": 0.0,8  "auto_map": {9    "AutoConfig": "configuration_codegen.CodeGenConfig",10    "AutoModel": "modeling_codegen.CodeGenModel",11    "AutoModelForCausalLM": "modeling_codegen.CodeGenForCausalLM"12  },13  "bos_token_id": 1,14  "embd_pdrop": 0.0,15  "eos_token_id": 2,16  "gradient_checkpointing": false,17  "initializer_range": 0.02,18  "layer_norm_epsilon": 1e-05,19  "model_type": "codegen",20  "n_ctx": 2048,21  "n_embd": 2560,22  "n_head": 32,23  "n_inner": null,24  "n_layer": 32,25  "n_positions": 2048,26  "resid_pdrop": 0.0,27  "rotary_dim": 64,28  "scale_attn_weights": true,29  "summary_activation": null,30  "summary_first_dropout": 0.1,31  "summary_proj_to_labels": true,32  "summary_type": "cls_index",33  "summary_use_proj": true,34  "task_specific_params": {35    "text-generation": {36      "do_sample": true,37      "max_length": 50,38      "temperature": 1.039    }40  },41  "tokenizer_class": "GPT2Tokenizer",42  "torch_dtype": "float32",43  "transformers_version": "4.18.0",44  "use_cache": true,45  "vocab_size": 5120046}47