Upload folder using huggingface_hub

config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 128009,
+  "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",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128004,
+  "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,
+  "transformers_version": "4.57.1",
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "vocab_size": 128256
+}

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42d7758e106550ec7dcb1fb217d6c06a1c4511d38a95adae3df4421a45b16198
+size 45359109

neuron_config.json

@@ -0,0 +1,27 @@
+{
+  "_serialized_key": "NxDNeuronConfig",
+  "batch_size": 1,
+  "capacity_factor": null,
+  "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
+  "checkpoint_revision": null,
+  "continuous_batching": false,
+  "ep_degree": 1,
+  "fused_qkv": false,
+  "glu_mlp": true,
+  "local_ranks_size": 2,
+  "max_batch_size": 1,
+  "max_context_length": 4096,
+  "max_topk": 256,
+  "n_active_tokens": 4096,
+  "neuronxcc_version": "2.21.18209.0+043b1bf7",
+  "on_device_sampling": false,
+  "optimum_neuron_version": "0.4.2.dev0",
+  "output_logits": false,
+  "pp_degree": 1,
+  "sequence_length": 4096,
+  "speculation_length": 0,
+  "start_rank_id": 0,
+  "target": "trn1",
+  "torch_dtype": "bfloat16",
+  "tp_degree": 2
+}