HelpingAI/Dhanishtha-Large
332
1{2 "architectures": [3 "Qwen2ForCausalLM"4 ],5 "attention_dropout": 0.0,6 "bos_token_id": 151643,7 "eos_token_id": 151643,8 "hidden_act": "silu",9 "hidden_size": 3584,10 "initializer_range": 0.02,11 "intermediate_size": 18944,12 "max_position_embeddings": 131072,13 "max_window_layers": 28,14 "model_type": "qwen2",15 "num_attention_heads": 28,16 "num_hidden_layers": 28,17 "num_key_value_heads": 4,18 "pad_token_id": 151654,19 "rms_norm_eps": 1e-06,20 "rope_scaling": null,21 "rope_theta": 10000,22 "sliding_window": null,23 "tie_word_embeddings": false,24 "torch_dtype": "bfloat16",25 "transformers_version": "4.49.0",26 "use_cache": true,27 "use_mrope": false,28 "use_sliding_window": false,29 "vocab_size": 15166530}31 