CoolFace
Modelpublic

thelamapi/next-14b

sourceHugging Facemitupdated 7mo agoView on Hugging Face
3likes35downloads
config.json75 linesDownload Raw Back to root
1{2  "architectures": [3    "Qwen3ForCausalLM"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "dtype": "bfloat16",8  "eos_token_id": 151645,9  "head_dim": 128,10  "hidden_act": "silu",11  "hidden_size": 5120,12  "initializer_range": 0.02,13  "intermediate_size": 17408,14  "layer_types": [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    "full_attention",43    "full_attention",44    "full_attention",45    "full_attention",46    "full_attention",47    "full_attention",48    "full_attention",49    "full_attention",50    "full_attention",51    "full_attention",52    "full_attention",53    "full_attention",54    "full_attention"55  ],56  "max_position_embeddings": 40960,57  "max_window_layers": 40,58  "model_type": "qwen3",59  "num_attention_heads": 40,60  "num_hidden_layers": 40,61  "num_key_value_heads": 8,62  "pad_token_id": 151654,63  "rms_norm_eps": 1e-06,64  "rope_scaling": null,65  "rope_theta": 1000000,66  "sliding_window": null,67  "tie_word_embeddings": false,68  "transformers_version": "4.57.1",69  "unsloth_fixed": true,70  "unsloth_version": "2025.11.1",71  "use_cache": true,72  "use_sliding_window": false,73  "vocab_size": 15193674}75