| { | |
| "_name_or_path": "optimum/mistral-1.1b-testing", | |
| "architectures": [ | |
| "MistralForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 5632, | |
| "max_position_embeddings": 32768, | |
| "model_type": "mistral", | |
| "neuron": { | |
| "auto_cast_type": "bf16", | |
| "batch_size": 4, | |
| "checkpoint_id": "optimum/mistral-1.1b-testing", | |
| "checkpoint_revision": "ce03bc8d47dbd2c173ff65f3a8de1325ba724195", | |
| "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": 22, | |
| "num_key_value_heads": 4, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.48.3", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |