zipaltrivedi/dotnet-coder-14b
101.8k
1{2 "architectures": [3 "Qwen2ForCausalLM"4 ],5 "attention_dropout": 0.0,6 "bos_token_id": 151643,7 "dtype": "float16",8 "eos_token_id": 151645,9 "hidden_act": "silu",10 "hidden_size": 5120,11 "initializer_range": 0.02,12 "intermediate_size": 13824,13 "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 "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 "full_attention",56 "full_attention",57 "full_attention",58 "full_attention",59 "full_attention",60 "full_attention",61 "full_attention"62 ],63 "max_position_embeddings": 32768,64 "max_window_layers": 48,65 "model_type": "qwen2",66 "num_attention_heads": 40,67 "num_hidden_layers": 48,68 "num_key_value_heads": 8,69 "pad_token_id": null,70 "rms_norm_eps": 1e-06,71 "rope_parameters": {72 "rope_theta": 1000000.0,73 "rope_type": "default"74 },75 "sliding_window": null,76 "tie_word_embeddings": false,77 "transformers_version": "5.5.1",78 "use_cache": true,79 "use_sliding_window": false,80 "vocab_size": 15206481}82 