| { | |
| "architectures": [ | |
| "ChartMoEForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_chartmoe.ChartMoEConfig", | |
| "AutoModel": "modeling_chartmoe.ChartMoEForCausalLM", | |
| "AutoModelForCausalLM": "modeling_chartmoe.ChartMoEForCausalLM" | |
| }, | |
| "bias": false, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_length": 4096, | |
| "max_position_embeddings": 32768, | |
| "model_type": "chartmoe", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 2, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 1.0, | |
| "type": "dynamic" | |
| }, | |
| "rope_theta": 1000000, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.33.1", | |
| "use_cache": false, | |
| "vocab_size": 92544, | |
| "img_size": 490, | |
| "num_experts": 4, | |
| "num_selected": 2 | |
| } | |