Upload MixFormerSequentialForCausalLM

config.json

@@ -1,27 +1,36 @@
 {
-  "_name_or_path": "PY007/TinyLlama-1.1B-Chat-v0.3",
+  "_name_or_path": "Open-Orca/oo-phi-1_5",
+  "activation_function": "gelu_new",
+  "architecture": {
+    "block_cls": "parallel",
+    "mixer": {},
+    "mlp": {
+      "mlp_cls": "mlp"
+    }
+  },
   "architectures": [
-    "LlamaForCausalLM"
+    "MixFormerSequentialForCausalLM"
   ],
-  "attention_bias": false,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "hidden_act": "silu",
-  "hidden_size": 2048,
+  "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,
   "initializer_range": 0.02,
-  "intermediate_size": 5632,
-  "max_position_embeddings": 2048,
-  "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 22,
-  "num_key_value_heads": 4,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "mixformer-sequential",
+  "n_embd": 2048,
+  "n_head": 32,
+  "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": "float16",
-  "transformers_version": "4.34.0",
-  "use_cache": false,
-  "vocab_size": 32003
+  "transformers_version": "4.34.1",
+  "use_cache": true,
+  "vocab_size": 50304
 }

generation_config.json

@@ -1,4 +1,4 @@
 {
-  "max_new_tokens": 32,
-  "transformers_version": "4.34.0"
+  "_from_model_config": true,
+  "transformers_version": "4.34.1"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74ca1ecb9a8cc7868aa8c2f11d1856a9058b61edc3a31a8996014056aae89062
-size 2200188849
+oid sha256:9ab31e1dc0fd25e1e60d49d774c7e528f70dfa69039ceef05c52e841a4d511bb
+size 2829287169