| { | |
| "_name_or_path": "/mnt/user/294761/finetune/deepseek-models/deepseek-coder-33b-base", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 32013, | |
| "eos_token": "<\uff5cend\u2581of\u2581sentence\uff5c>", | |
| "eos_token_id": 32014, | |
| "hidden_act": "silu", | |
| "hidden_size": 7168, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 19200, | |
| "max_position_embeddings": 16384, | |
| "model_type": "llama", | |
| "num_attention_heads": 56, | |
| "num_hidden_layers": 62, | |
| "num_key_value_heads": 8, | |
| "pad_token": "<\uff5cend\u2581of\u2581sentence\uff5c>", | |
| "pad_token_id": 32014, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "factor": 4.0, | |
| "type": "linear" | |
| }, | |
| "rope_theta": 100000, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.36.0", | |
| "use_cache": true, | |
| "vocab_size": 32256 | |
| } | |