CoolFace
Modelpublic

Scriptease/colorhex-1b

sourceHugging Facegemmaupdated 1mo agoView on Hugging Face
1likes269downloads
config.json74 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  "cache_implementation": "hybrid",11  "dtype": "bfloat16",12  "eos_token_id": 106,13  "final_logit_softcapping": null,14  "head_dim": 256,15  "hidden_activation": "gelu_pytorch_tanh",16  "hidden_size": 1152,17  "initializer_range": 0.02,18  "intermediate_size": 6912,19  "layer_types": [20    "sliding_attention",21    "sliding_attention",22    "sliding_attention",23    "sliding_attention",24    "sliding_attention",25    "full_attention",26    "sliding_attention",27    "sliding_attention",28    "sliding_attention",29    "sliding_attention",30    "sliding_attention",31    "full_attention",32    "sliding_attention",33    "sliding_attention",34    "sliding_attention",35    "sliding_attention",36    "sliding_attention",37    "full_attention",38    "sliding_attention",39    "sliding_attention",40    "sliding_attention",41    "sliding_attention",42    "sliding_attention",43    "full_attention",44    "sliding_attention",45    "sliding_attention"46  ],47  "max_position_embeddings": 32768,48  "model_type": "gemma3_text",49  "num_attention_heads": 4,50  "num_hidden_layers": 26,51  "num_key_value_heads": 1,52  "pad_token_id": 0,53  "query_pre_attn_scalar": 256,54  "rms_norm_eps": 1e-06,55  "rope_parameters": {56    "full_attention": {57      "rope_theta": 1000000,58      "rope_type": "default"59    },60    "sliding_attention": {61      "rope_theta": 10000,62      "rope_type": "default"63    }64  },65  "sliding_window": 512,66  "sliding_window_pattern": 6,67  "tie_word_embeddings": true,68  "transformers_version": "5.15.1",69  "unsloth_fixed": true,70  "use_bidirectional_attention": false,71  "use_cache": true,72  "vocab_size": 26214473}74