optimum-neuron-cache / neuronxcc-2.19.8089.0+8ab9f450 /0_REGISTRY /0.3.1.dev5 /smollm3 /HuggingFaceTB /SmolLM3-3B /7cf30abbc0e808430a49.json
| { | |
| "_entry_class": "SingleModelCacheEntry", | |
| "_model_id": "HuggingFaceTB/SmolLM3-3B", | |
| "_task": "text-generation", | |
| "architectures": [ | |
| "SmolLM3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 65536, | |
| "max_window_layers": 28, | |
| "mlp_bias": false, | |
| "model_type": "smollm3", | |
| "neuron": { | |
| "_serialized_key": "NxDNeuronConfig", | |
| "async_mode": false, | |
| "attn_kernel_enabled": false, | |
| "batch_size": 4, | |
| "capacity_factor": null, | |
| "cc_pipeline_tiling_factor": 2, | |
| "checkpoint_id": "HuggingFaceTB/SmolLM3-3B", | |
| "checkpoint_revision": "1c00fc78bd9cf90108046bc433cb34992480f1c1", | |
| "continuous_batching": true, | |
| "enable_bucketing": false, | |
| "ep_degree": 1, | |
| "flash_decoding_enabled": false, | |
| "fused_qkv": true, | |
| "glu_mlp": true, | |
| "is_chunked_prefill": false, | |
| "local_ranks_size": 2, | |
| "logical_nc_config": 1, | |
| "max_batch_size": 4, | |
| "max_context_length": 4096, | |
| "max_topk": 256, | |
| "n_active_tokens": 4096, | |
| "neuronxcc_version": "2.19.8089.0+8ab9f450", | |
| "num_cores_per_group": 1, | |
| "on_device_sampling": true, | |
| "optimum_neuron_version": "0.3.1.dev5", | |
| "output_logits": false, | |
| "pp_degree": 1, | |
| "qkv_kernel_enabled": false, | |
| "sequence_length": 4096, | |
| "sequence_parallel_enabled": false, | |
| "speculation_length": 0, | |
| "start_rank_id": 0, | |
| "target": null, | |
| "torch_dtype": "bfloat16", | |
| "tp_degree": 2 | |
| }, | |
| "no_rope_layer_interval": 4, | |
| "no_rope_layers": [ | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0 | |
| ], | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 4, | |
| "pretraining_tp": 2, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 5000000.0, | |
| "sliding_window": null, | |
| "use_cache": false, | |
| "use_sliding_window": false, | |
| "vocab_size": 128256 | |
| } |