CoolFace
Modelpublic

Rev3auth/iris_16bit

sourceHugging Faceapache-2.0updated 12d agoView on Hugging Face
0likes164downloads
config.json54 linesDownload Raw Back to root
1{2    "_sliding_window_pattern": 6,3    "architectures": [4        "Gemma3ForCausalLM"5    ],6    "attention_bias": false,7    "attention_dropout": 0.0,8    "attn_logit_softcapping": null,9    "bos_token_id": 2,10    "torch_dtype": "bfloat16",11    "eos_token_id": 106,12    "final_logit_softcapping": null,13    "head_dim": 256,14    "hidden_activation": "gelu_pytorch_tanh",15    "hidden_size": 640,16    "initializer_range": 0.02,17    "intermediate_size": 2048,18    "layer_types": [19        "sliding_attention",20        "sliding_attention",21        "sliding_attention",22        "sliding_attention",23        "sliding_attention",24        "full_attention",25        "sliding_attention",26        "sliding_attention",27        "sliding_attention",28        "sliding_attention",29        "sliding_attention",30        "full_attention",31        "sliding_attention",32        "sliding_attention",33        "sliding_attention",34        "sliding_attention",35        "sliding_attention",36        "full_attention"37    ],38    "max_position_embeddings": 32768,39    "model_type": "gemma3_text",40    "num_attention_heads": 4,41    "num_hidden_layers": 18,42    "num_key_value_heads": 1,43    "pad_token_id": 0,44    "query_pre_attn_scalar": 256,45    "rms_norm_eps": 1e-06,46    "rope_local_base_freq": 10000.0,47    "rope_scaling": null,48    "rope_theta": 1000000.0,49    "sliding_window": 512,50    "unsloth_fixed": true,51    "use_bidirectional_attention": false,52    "use_cache": true,53    "vocab_size": 26214454}