| { | |
| "_name_or_path": "ibm-granite/granite-3.1-2b-instruct", | |
| "architectures": [ | |
| "GraniteForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.1, | |
| "attention_multiplier": 0.015625, | |
| "bos_token_id": 0, | |
| "embedding_multiplier": 12.0, | |
| "eos_token_id": 0, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "logits_scaling": 8.0, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "granite", | |
| "neuron": { | |
| "auto_cast_type": "bf16", | |
| "batch_size": 4, | |
| "checkpoint_id": "ibm-granite/granite-3.1-2b-instruct", | |
| "checkpoint_revision": "07eae41278b4cd918dbe32da5d77c27e1379f751", | |
| "compiler_type": "neuronx-cc", | |
| "compiler_version": "2.15.143.0+e39249ad", | |
| "num_cores": 2, | |
| "sequence_length": 4096, | |
| "task": "text-generation" | |
| }, | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 0, | |
| "residual_multiplier": 0.22, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 5000000.0, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.48.3", | |
| "use_cache": true, | |
| "vocab_size": 49155 | |
| } | |