CoolFace
Modelpublic

lostargon/Tiny-Jev

sourceHugging Faceapache-2.0updated 16h agoView on Hugging Face
4likes719downloads
config.json71 linesDownload Raw Back to root
1{2  "architectures": [3    "TinyJevModel"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "auto_map": {8    "AutoConfig": "modeling_tiny_jev.TinyJevConfig",9    "AutoModel": "modeling_tiny_jev.TinyJevModel"10  },11  "bos_token_id": 151643,12  "cue": " - correct?",13  "dtype": "bfloat16",14  "eos_token_id": 151645,15  "head_dim": 128,16  "hidden_act": "silu",17  "hidden_size": 1024,18  "initializer_range": 0.02,19  "intermediate_size": 3072,20  "layer_types": [21    "full_attention",22    "full_attention",23    "full_attention",24    "full_attention",25    "full_attention",26    "full_attention",27    "full_attention",28    "full_attention",29    "full_attention",30    "full_attention",31    "full_attention",32    "full_attention",33    "full_attention",34    "full_attention",35    "full_attention",36    "full_attention",37    "full_attention",38    "full_attention",39    "full_attention",40    "full_attention",41    "full_attention",42    "full_attention",43    "full_attention",44    "full_attention",45    "full_attention",46    "full_attention",47    "full_attention",48    "full_attention"49  ],50  "max_position_embeddings": 40960,51  "max_window_layers": 28,52  "model_type": "tiny_jev",53  "num_attention_heads": 16,54  "num_hidden_layers": 28,55  "num_key_value_heads": 8,56  "opt_token": "<opt>",57  "pad_token_id": null,58  "rms_norm_eps": 1e-06,59  "rope_parameters": {60    "rope_theta": 1000000,61    "rope_type": "default"62  },63  "sliding_window": null,64  "temperature": 0.95,65  "tie_word_embeddings": true,66  "transformers_version": "5.17.0",67  "use_cache": true,68  "use_sliding_window": false,69  "vocab_size": 15167070}71