optimum-intel-internal-testing/tiny-random-codegen2

1{2  "_name_or_path": "/home/ea/work/my_optimum_intel/optimum-intel/codegen2-1b",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  "head_dim": 32,18  "initializer_range": 0.02,19  "layer_norm_epsilon": 1e-05,20  "model_type": "codegen",21  "n_ctx": 512,22  "n_embd": 32,23  "n_head": 8,24  "n_inner": null,25  "n_layer": 2,26  "n_positions": 512,27  "resid_pdrop": 0.0,28  "rotary_dim": 4,29  "scale_attn_weights": true,30  "summary_activation": null,31  "summary_first_dropout": 0.1,32  "summary_proj_to_labels": true,33  "summary_type": "cls_index",34  "summary_use_proj": true,35  "task_specific_params": {36    "text-generation": {37      "do_sample": true,38      "max_length": 50,39      "temperature": 1.040    }41  },42  "tie_word_embeddings": false,43  "tokenizer_class": "GPT2Tokenizer",44  "torch_dtype": "float32",45  "transformers_version": "4.40.2",46  "trust_remote_code": true,47  "use_cache": true,48  "vocab_size": 5120049}50