Upload MixFormerSequentialForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "phi-1.5-half",
+  "_name_or_path": "microsoft/phi-1_5",
   "activation_function": "gelu_new",
   "architecture": {
     "block_cls": "parallel",
@@ -12,8 +12,8 @@
     "MixFormerSequentialForCausalLM"
   ],
   "auto_map": {
-    "AutoConfig": "configuration_mixformer_sequential.MixFormerSequentialConfig",
-    "AutoModelForCausalLM": "modeling_mixformer_sequential.MixFormerSequentialForCausalLM"
+    "AutoConfig": "microsoft/phi-1_5--configuration_mixformer_sequential.MixFormerSequentialConfig",
+    "AutoModelForCausalLM": "microsoft/phi-1_5--modeling_mixformer_sequential.MixFormerSequentialForCausalLM"
   },
   "embd_layer": "default",
   "embd_pdrop": 0.0,
@@ -29,7 +29,7 @@
   "resid_pdrop": 0.0,
   "rotary_dim": 32,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.32.1",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.0.dev0",
   "vocab_size": 51200
 }

generation_config.json

@@ -1,4 +1,4 @@
 {
   "_from_model_config": true,
-  "transformers_version": "4.32.1"
+  "transformers_version": "4.34.0.dev0"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2d4c3c769ef4a9f7e1d33af3a305de5c279306829a8dd78811040a2e95d4e0c
-size 5253626297
+oid sha256:1e0e2d756e4e531f8f949541c592165b61c3b6f7ac2f556fd68f2543a8ec3fb3
+size 5253706317