Synchronizing local compiler cache.
Browse files
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24/inference/llama/LargeWorldModel/LWM-Text-Chat-1M/85cee1378c49e9bd9345.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 1048576, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "LargeWorldModel/LWM-Text-Chat-1M", "checkpoint_revision": "0598c443b02aeb1a1f9f6788e9af85ea762a452d", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pad_token_id": 0, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 50000000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}
|