CoolFace
Modelpublic

Iambackup/RetroDFM-R-8B

sourceHugging Facegpl-3.0updated 2mo agoView on Hugging Face
0likes14downloads
config.json70 linesDownload Raw Back to root
1{2  "architectures": [3    "Qwen3ForCausalLM"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "bos_token_id": 151643,8  "dtype": "bfloat16",9  "eos_token_id": 151645,10  "head_dim": 128,11  "hidden_act": "silu",12  "hidden_size": 4096,13  "initializer_range": 0.02,14  "intermediate_size": 12288,15  "layer_types": [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  ],53  "max_position_embeddings": 40960,54  "max_window_layers": 36,55  "model_type": "qwen3",56  "num_attention_heads": 32,57  "num_hidden_layers": 36,58  "num_key_value_heads": 8,59  "pad_token_id": 151643,60  "rms_norm_eps": 1e-06,61  "rope_scaling": null,62  "rope_theta": 1000000,63  "sliding_window": null,64  "tie_word_embeddings": false,65  "transformers_version": "4.57.0",66  "use_cache": false,67  "use_sliding_window": false,68  "vocab_size": 15193669}70