CoolFace
Modelpublic

asadullahdogarr/adaption_codeintel_python_reasoning_v

sourceHugging Faceotherupdated 2mo agoView on Hugging Face
0likes6downloads
config.json82 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  "dtype": "bfloat16",11  "eos_token_id": 1,12  "final_logit_softcapping": null,13  "head_dim": 256,14  "hidden_activation": "gelu_pytorch_tanh",15  "hidden_size": 2560,16  "initializer_range": 0.02,17  "intermediate_size": 10240,18  "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    "sliding_attention",38    "sliding_attention",39    "sliding_attention",40    "sliding_attention",41    "sliding_attention",42    "full_attention",43    "sliding_attention",44    "sliding_attention",45    "sliding_attention",46    "sliding_attention",47    "sliding_attention",48    "full_attention",49    "sliding_attention",50    "sliding_attention",51    "sliding_attention",52    "sliding_attention"53  ],54  "max_position_embeddings": 131072,55  "mm_tokens_per_image": 256,56  "model_type": "gemma3_text",57  "num_attention_heads": 8,58  "num_hidden_layers": 34,59  "num_key_value_heads": 4,60  "pad_token_id": 0,61  "query_pre_attn_scalar": 256,62  "rms_norm_eps": 1e-06,63  "rope_parameters": {64    "full_attention": {65      "factor": 8.0,66      "rope_theta": 1000000.0,67      "rope_type": "linear"68    },69    "sliding_attention": {70      "rope_theta": 10000.0,71      "rope_type": "default"72    }73  },74  "sliding_window": 1024,75  "tie_word_embeddings": true,76  "transformers_version": "5.13.0",77  "use_bidirectional_attention": false,78  "use_cache": false,79  "vocab_size": 262208,80  "torch_dtype": "bfloat16"81}82