{ "architectures": [ "StableLmForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 100257, "dtype": "bfloat16", "eos_token_id": 100278, "hidden_act": "silu", "hidden_dropout": 0.0, "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 5632, "layer_norm_eps": 1e-05, "max_position_embeddings": 4096, "model_type": "stablelm", "num_attention_heads": 32, "num_hidden_layers": 24, "num_key_value_heads": 32, "pad_token_id": null, "partial_rotary_factor": 0.25, "qk_layernorm": false, "rope_parameters": { "partial_rotary_factor": 0.25, "rope_theta": 10000, "rope_type": "default" }, "tie_word_embeddings": false, "transformers_version": "5.13.1", "use_cache": true, "use_parallel_residual": false, "use_qkv_bias": true, "vocab_size": 100352 }