CoolFace
Modelpublic

coderian/axiom-python-1.5B

sourceHugging Faceapache-2.0updated 9d agoView on Hugging Face
0likes333downloads
config.json63 linesDownload Raw Back to root
1{2  "architectures": [3    "Qwen2ForCausalLM"4  ],5  "attention_dropout": 0.0,6  "bos_token_id": 151643,7  "dtype": "float16",8  "eos_token_id": 151643,9  "hidden_act": "silu",10  "hidden_size": 1536,11  "initializer_range": 0.02,12  "intermediate_size": 8960,13  "layer_types": [14    "full_attention",15    "full_attention",16    "full_attention",17    "full_attention",18    "full_attention",19    "full_attention",20    "full_attention",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  ],43  "max_position_embeddings": 131072,44  "max_window_layers": 28,45  "model_type": "qwen2",46  "num_attention_heads": 12,47  "num_hidden_layers": 28,48  "num_key_value_heads": 2,49  "pad_token_id": null,50  "rms_norm_eps": 1e-06,51  "rope_parameters": {52    "rope_theta": 1000000.0,53    "rope_type": "default"54  },55  "sliding_window": null,56  "tie_word_embeddings": true,57  "transformers_version": "5.17.0",58  "use_cache": true,59  "use_mrope": false,60  "use_sliding_window": false,61  "vocab_size": 15193662}63