littlelearner/littlelearner-1.3b-base
1298
1{2 "architectures": [3 "Qwen3ForCausalLM"4 ],5 "attention_bias": false,6 "attention_dropout": 0.0,7 "bos_token_id": 0,8 "dtype": "bfloat16",9 "eos_token_id": 0,10 "head_dim": 128,11 "hidden_act": "silu",12 "hidden_size": 2048,13 "initializer_range": 0.02,14 "intermediate_size": 5632,15 "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 ],43 "max_position_embeddings": 4096,44 "max_window_layers": 28,45 "model_type": "qwen3",46 "num_attention_heads": 16,47 "num_hidden_layers": 26,48 "num_key_value_heads": 8,49 "pad_token_id": 1,50 "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": "5.2.0",58 "use_cache": true,59 "use_sliding_window": false,60 "vocab_size": 64000,61 "rope_theta": 1000000.062}