usermma/Vibe-Coding-Claude-Fable-5-mlx-4Bit
062
1{2 "architectures": [3 "Qwen2ForCausalLM"4 ],5 "attention_dropout": 0.0,6 "bos_token_id": 151643,7 "dtype": "bfloat16",8 "eos_token_id": [9 151645,10 15164311 ],12 "hidden_act": "silu",13 "hidden_size": 3584,14 "initializer_range": 0.02,15 "intermediate_size": 18944,16 "layer_types": [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 ],46 "max_position_embeddings": 32768,47 "max_window_layers": 28,48 "model_type": "qwen2",49 "num_attention_heads": 28,50 "num_hidden_layers": 28,51 "num_key_value_heads": 4,52 "pad_token_id": null,53 "quantization": {54 "group_size": 64,55 "bits": 4,56 "mode": "affine"57 },58 "quantization_config": {59 "group_size": 64,60 "bits": 4,61 "mode": "affine"62 },63 "rms_norm_eps": 1e-06,64 "rope_parameters": {65 "rope_theta": 1000000.0,66 "rope_type": "default"67 },68 "sliding_window": null,69 "tie_word_embeddings": false,70 "transformers_version": "5.11.0",71 "use_cache": true,72 "use_sliding_window": false,73 "vocab_size": 15206474}