Add Neuron-optimized files for microsoft/Phi-3-mini-128k-instruct

🤖 Neuron Export Bot: Adding AWS Neuron-optimized model files.

Original model: [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct)
Task: text-generation
Generated by: [badaoui](https://huggingface.co/badaoui)
Generated using: [Optimum Neuron Compiler Space](https://huggingface.co/spaces/optimum/neuron-export)

These files have been pre-compiled for AWS Neuron devices (Inferentia/Trainium) and should provide improved inference performance.

README.md

@@ -0,0 +1,38 @@
+---
+tags:
+- neuron
+- optimized
+- aws-neuron
+- text-generation
+base_model: microsoft/Phi-3-mini-128k-instruct
+---
+
+# Neuron-Optimized microsoft/Phi-3-mini-128k-instruct
+
+This repository contains AWS Neuron-optimized files for [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct).
+
+## Model Details
+
+- **Base Model**: [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct)
+- **Task**: text-generation
+- **Optimization**: AWS Neuron compilation
+- **Generated by**: [badaoui](https://huggingface.co/badaoui)
+- **Generated using**: [Optimum Neuron Compiler Space](https://huggingface.co/spaces/optimum/neuron-export)
+
+## Usage
+
+This model has been optimized for AWS Neuron devices (Inferentia/Trainium). To use it:
+
+```python
+from optimum.neuron import NeuronModelForCausalLM
+
+model = NeuronModelForCausalLM.from_pretrained("badaoui/microsoft-Phi-3-mini-128k-instruct-neuron")
+```
+
+## Performance
+
+These files are pre-compiled for AWS Neuron devices and should provide improved inference performance compared to the original model when deployed on Inferentia or Trainium instances.
+
+## Original Model
+
+For the original model, training details, and more information, please visit: [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct)

config.json

@@ -0,0 +1,138 @@
+{
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/Phi-3-mini-128k-instruct--configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "model_type": "phi3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "long_factor": [
+      1.0700000524520874,
+      1.1200000047683716,
+      1.149999976158142,
+      1.4199999570846558,
+      1.5699999332427979,
+      1.7999999523162842,
+      2.129999876022339,
+      2.129999876022339,
+      3.009999990463257,
+      5.910000324249268,
+      6.950000286102295,
+      9.070000648498535,
+      9.930000305175781,
+      10.710000038146973,
+      11.130000114440918,
+      14.609999656677246,
+      15.409998893737793,
+      19.809999465942383,
+      37.279998779296875,
+      38.279998779296875,
+      38.599998474121094,
+      40.12000274658203,
+      46.20000457763672,
+      50.940006256103516,
+      53.66000747680664,
+      54.9373893737793,
+      56.89738845825195,
+      57.28738784790039,
+      59.98738479614258,
+      60.86738586425781,
+      60.887386322021484,
+      61.71739196777344,
+      62.91739273071289,
+      62.957393646240234,
+      63.41739273071289,
+      63.8173942565918,
+      63.83739471435547,
+      63.897396087646484,
+      63.93739700317383,
+      64.06739807128906,
+      64.11434936523438,
+      64.12435150146484,
+      64.15435028076172,
+      64.19435119628906,
+      64.24435424804688,
+      64.57435607910156,
+      64.69000244140625,
+      64.76000213623047
+    ],
+    "short_factor": [
+      1.1,
+      1.1,
+      1.1,
+      1.3000000000000003,
+      1.3500000000000003,
+      1.3500000000000003,
+      1.4000000000000004,
+      1.5500000000000005,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.0500000000000007,
+      2.0500000000000007,
+      2.0500000000000007,
+      2.0500000000000007,
+      2.0500000000000007,
+      2.0500000000000007,
+      2.1000000000000005,
+      2.1000000000000005,
+      2.1500000000000004,
+      2.25,
+      2.25,
+      2.25,
+      2.25,
+      2.25,
+      2.3999999999999995,
+      2.4499999999999993,
+      2.499999999999999,
+      2.6999999999999984,
+      2.6999999999999984,
+      2.7499999999999982,
+      2.799999999999998,
+      2.8999999999999977,
+      3.049999999999997
+    ],
+    "type": "longrope"
+  },
+  "rope_theta": 10000.0,
+  "sliding_window": 262144,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 32064
+}

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d441dca8eb2103b57a5b71b057143c66da6026bdea0f371724c06769d07b3cdc
+size 8013157559

neuron_config.json

@@ -0,0 +1,43 @@
+{
+  "_serialized_key": "NxDNeuronConfig",
+  "async_mode": false,
+  "attn_kernel_enabled": false,
+  "batch_size": 1,
+  "capacity_factor": null,
+  "cc_pipeline_tiling_factor": 2,
+  "checkpoint_id": "microsoft/Phi-3-mini-128k-instruct",
+  "checkpoint_revision": "072cb7562cb8c4adf682a8e186aaafa49469eb5d",
+  "continuous_batching": false,
+  "enable_bucketing": false,
+  "ep_degree": 1,
+  "flash_decoding_enabled": false,
+  "fused_qkv": true,
+  "glu_mlp": true,
+  "is_chunked_prefill": false,
+  "local_ranks_size": 12,
+  "logical_nc_config": 1,
+  "max_batch_size": 1,
+  "max_context_length": 128,
+  "max_topk": 256,
+  "mlp_kernel_enabled": false,
+  "mlp_kernel_fuse_residual_add": false,
+  "n_active_tokens": 128,
+  "neuronxcc_version": "2.19.8089.0+8ab9f450",
+  "num_cores_per_group": 1,
+  "on_device_sampling": true,
+  "optimum_neuron_version": "0.3.0",
+  "output_logits": false,
+  "padding_side": "right",
+  "pp_degree": 1,
+  "qk_layernorm": false,
+  "qkv_kernel_enabled": false,
+  "rpl_reduce_dtype": "bfloat16",
+  "sequence_length": 128,
+  "sequence_parallel_enabled": false,
+  "speculation_length": 0,
+  "start_rank_id": 0,
+  "target": null,
+  "torch_dtype": "bfloat16",
+  "tp_degree": 12,
+  "vocab_parallel": false
+}