| { | |
| "_name_or_path": "AlumiK/LingLong-317M-Chat", | |
| "activation_function": "gelu_new", | |
| "architectures": [ | |
| "LingLongForCausalLM" | |
| ], | |
| "attn_c": 8, | |
| "attn_mode": "sparse", | |
| "attn_pdrop": 0.1, | |
| "attn_stride": 128, | |
| "auto_map": { | |
| "AutoConfig": "configuration_linglong.LingLongConfig", | |
| "AutoModelForCausalLM": "modeling_linglong.LingLongForCausalLM" | |
| }, | |
| "backward": false, | |
| "bos_token_id": 10, | |
| "embd_pdrop": 0.1, | |
| "eos_token_id": 8, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-08, | |
| "model_type": "linglong", | |
| "n_embd": 1024, | |
| "n_head": 16, | |
| "n_inner": null, | |
| "n_layer": 24, | |
| "n_position": 1024, | |
| "pad_token_id": 0, | |
| "reorder_and_upcast_attn": false, | |
| "resid_pdrop": 0.1, | |
| "scale_attn_by_inverse_layer_idx": false, | |
| "scale_attn_weights": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.40.2", | |
| "use_cache": true, | |
| "use_pinyin": false, | |
| "vocab_size": 13312 | |
| } | |