Upload MixFormerSequentialForCausalLM

config.json

@@ -1,35 +1,30 @@
 {
   "_name_or_path": "microsoft/phi-1_5",
   "activation_function": "gelu_new",
-  "architecture": {
-    "block_cls": "parallel",
-    "mixer": {},
-    "mlp": {
-      "mlp_cls": "mlp"
-    }
-  },
   "architectures": [
     "MixFormerSequentialForCausalLM"
   ],
+  "attn_pdrop": 0.0,
   "auto_map": {
     "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,
+  "flash_rotary": false,
+  "fused_dense": false,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "mixformer-sequential",
   "n_embd": 2048,
   "n_head": 32,
+  "n_head_kv": null,
   "n_inner": null,
   "n_layer": 24,
   "n_positions": 2048,
-  "phyagi_version": "0.0.4.dev",
   "resid_pdrop": 0.0,
   "rotary_dim": 32,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.33.1",
+  "transformers_version": "4.34.1",
   "vocab_size": 51200
 }

generation_config.json

@@ -1,4 +1,4 @@
 {
   "_from_model_config": true,
-  "transformers_version": "4.33.1"
+  "transformers_version": "4.34.1"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7db1a628a23bf56cdba7c12063d81436873d78b48ecfc1d09415b344b52ec28a
-size 5673167489
+oid sha256:a3236303f601e7522d6dc0575b39970f7f9c83fd18a0005c360d44a87d24fb0c
+size 5673158870