| { | |
| "_name_or_path": "xverse/XVERSE-13B-256K", | |
| "architectures": [ | |
| "XverseForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "xverse/XVERSE-13B-256K--configuration_xverse.XverseConfig", | |
| "AutoModelForCausalLM": "xverse/XVERSE-13B-256K--modeling_xverse.XverseForCausalLM" | |
| }, | |
| "bos_token_id": 2, | |
| "eos_token_id": 3, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 13824, | |
| "max_position_embeddings": 32768, | |
| "max_tokenizer_truncation": 262144, | |
| "model_type": "xverse", | |
| "num_attention_heads": 40, | |
| "num_hidden_layers": 40, | |
| "pad_token_id": 1, | |
| "rms_norm_eps": 1e-06, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.31.0", | |
| "use_cache": false, | |
| "vocab_size": 100534 | |
| } | |