{ "_name_or_path": "Ganga-2-1B-PreAlpha_v0.1", "architectures": [ "MistralForCausalLM" ], "attention_dropout": 0.2, "bos_token_id": 6, "eos_token_id": 3, "head_dim": 64, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 7168, "max_position_embeddings": 2048, "model_type": "mistral", "num_attention_heads": 32, "num_hidden_layers": 16, "num_key_value_heads": 8, "pad_token_id": 0, "rms_norm_eps": 1e-06, "rope_theta": 10000.0, "sliding_window": 1024, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.48.2", "use_cache": true, "vocab_size": 32768 }