Delete neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev1

neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev1/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/3310d05484c3f0d11dcf.json

@@ -1,63 +0,0 @@
-{
-  "_entry_class": "SingleModelCacheEntry",
-  "_model_id": "unsloth/Llama-3.2-1B-Instruct",
-  "_task": "text-generation",
-  "architectures": [
-    "LlamaForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "dtype": "bfloat16",
-  "head_dim": 64,
-  "hidden_act": "silu",
-  "hidden_size": 2048,
-  "initializer_range": 0.02,
-  "intermediate_size": 8192,
-  "max_position_embeddings": 131072,
-  "mlp_bias": false,
-  "model_type": "llama",
-  "neuron": {
-    "_serialized_key": "NxDNeuronConfig",
-    "batch_size": 1,
-    "capacity_factor": null,
-    "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
-    "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c",
-    "continuous_batching": false,
-    "ep_degree": 1,
-    "fused_qkv": true,
-    "glu_mlp": true,
-    "local_ranks_size": 1,
-    "max_batch_size": 1,
-    "max_context_length": 4096,
-    "max_topk": 256,
-    "n_active_tokens": 4096,
-    "neuronxcc_version": "2.21.33363.0+82129205",
-    "on_device_sampling": true,
-    "optimum_neuron_version": "0.4.5.dev1",
-    "output_logits": false,
-    "pp_degree": 1,
-    "sequence_length": 4096,
-    "speculation_length": 0,
-    "start_rank_id": 0,
-    "target": "trn1",
-    "torch_dtype": "bfloat16",
-    "tp_degree": 1
-  },
-  "num_attention_heads": 32,
-  "num_hidden_layers": 16,
-  "num_key_value_heads": 8,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 32.0,
-    "high_freq_factor": 4.0,
-    "low_freq_factor": 1.0,
-    "original_max_position_embeddings": 8192,
-    "rope_type": "llama3"
-  },
-  "rope_theta": 500000.0,
-  "tie_word_embeddings": true,
-  "unsloth_fixed": true,
-  "use_cache": true,
-  "vocab_size": 128256
-}