Upload 3 files

.gitattributes

@@ -37,3 +37,4 @@ tokenizer.json filter=lfs diff=lfs merge=lfs -text
 phi4-mini-8dq4w.pte filter=lfs diff=lfs merge=lfs -text
 phi4-mini-8da4w.pte filter=lfs diff=lfs merge=lfs -text
 phi4-mini-INT8-INT4.pte filter=lfs diff=lfs merge=lfs -text
+model.pte filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,226 @@
+{
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM",
+    "AutoTokenizer": "Xenova/gpt-4o"
+  },
+  "bos_token_id": 199999,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.0,
+  "eos_token_id": 199999,
+  "full_attn_mod": 1,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "interpolate_factor": 1,
+  "lm_head_bias": false,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "phi3",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 199999,
+  "partial_rotary_factor": 0.75,
+  "quantization_config": {
+    "include_input_output_embeddings": true,
+    "modules_to_not_convert": [],
+    "quant_method": "torchao",
+    "quant_type": {
+      "default": {
+        "_data": {
+          "module_fqn_to_config": {
+            "_default": {
+              "_data": {
+                "act_mapping_type": {
+                  "_data": "ASYMMETRIC",
+                  "_type": "MappingType"
+                },
+                "intx_packing_format": {
+                  "_data": "UNPACKED_TO_INT8",
+                  "_type": "IntxPackingFormat"
+                },
+                "layout": {
+                  "_data": {},
+                  "_type": "QDQLayout",
+                  "_version": 1
+                },
+                "weight_dtype": {
+                  "_data": "int4",
+                  "_type": "torch.dtype"
+                },
+                "weight_granularity": {
+                  "_data": {
+                    "group_size": 32
+                  },
+                  "_type": "PerGroup",
+                  "_version": 1
+                },
+                "weight_mapping_type": {
+                  "_data": "SYMMETRIC",
+                  "_type": "MappingType"
+                },
+                "weight_scale_dtype": null
+              },
+              "_type": "Int8DynamicActivationIntxWeightConfig",
+              "_version": 2
+            },
+            "model.embed_tokens": {
+              "_data": {
+                "granularity": {
+                  "_data": {
+                    "axis": 0
+                  },
+                  "_type": "PerAxis",
+                  "_version": 1
+                },
+                "intx_packing_format": {
+                  "_data": "UNPACKED_TO_INT8",
+                  "_type": "IntxPackingFormat"
+                },
+                "layout": {
+                  "_data": {},
+                  "_type": "QDQLayout",
+                  "_version": 1
+                },
+                "mapping_type": {
+                  "_data": "SYMMETRIC",
+                  "_type": "MappingType"
+                },
+                "scale_dtype": null,
+                "weight_dtype": {
+                  "_data": "int8",
+                  "_type": "torch.dtype"
+                }
+              },
+              "_type": "IntxWeightOnlyConfig",
+              "_version": 2
+            }
+          }
+        },
+        "_type": "ModuleFqnToConfig",
+        "_version": 1
+      }
+    },
+    "quant_type_kwargs": {},
+    "untie_embedding_weights": false
+  },
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "long_factor": [
+      1,
+      1.118320672,
+      1.250641126,
+      1.398617824,
+      1.564103225,
+      1.74916897,
+      1.956131817,
+      2.187582649,
+      2.446418898,
+      2.735880826,
+      3.059592084,
+      3.421605075,
+      3.826451687,
+      4.279200023,
+      4.785517845,
+      5.351743533,
+      5.984965424,
+      6.693110555,
+      7.485043894,
+      8.370679318,
+      9.36110372,
+      10.4687158,
+      11.70738129,
+      13.09260651,
+      14.64173252,
+      16.37415215,
+      18.31155283,
+      20.47818807,
+      22.90118105,
+      25.61086418,
+      28.64115884,
+      32.03,
+      32.1,
+      32.13,
+      32.23,
+      32.6,
+      32.61,
+      32.64,
+      32.66,
+      32.7,
+      32.71,
+      32.93,
+      32.97,
+      33.28,
+      33.49,
+      33.5,
+      44.16,
+      47.77
+    ],
+    "short_factor": [
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0,
+      1.0
+    ],
+    "type": "longrope"
+  },
+  "rope_theta": 10000.0,
+  "sliding_window": 262144,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0.dev0",
+  "use_cache": true,
+  "vocab_size": 200064
+}

model.pte

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f80c332e047191b69da17dee8c735cf2d4f4eee96a0afbf41774587b7e95713
+size 2776887680

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d8fcaa969952525984dc0db8398909b97646378bd703cfc21aff30c9ea911a4
+size 4811184887