add configs to repo (#4)

- add configs to repo (c29e855eceabf0a349cada410cdca6098952289d)
- Update puffin-phi-v2.json (07417bc3dfe99c855db8455b3bfda9987cddf69d)
- Update phi-1_5.json (dd4b01c10d4ad1ac9cd0d4ebfcdc7fff12c39690)
- Update puffin-phi-v2.json (0b6ab754f88c25bcd87cb5ccd8695821f63b9430)
- Update phi-1_5.json (292c78a6c9858a30f05b5a6f75f2cabfe4a1e567)
- Update phi-1_5.json (4ae008ee37ceb35f3a132731fab4050ca657035d)
- Update puffin-phi-v2.json (c9e49a07db5b7b79b42a9ea72fe07938036d1c47)


Co-authored-by: Radamés Ajna <[email protected]>

phi-1_5.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "phi-1.5-half",
+  "activation_function": "gelu",
+  "architectures": [
+    "MixFormerSequentialForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_mixformer_sequential.MixFormerSequentialConfig",
+    "AutoModelForCausalLM": "modeling_mixformer_sequential.MixFormerSequentialForCausalLM"
+  },
+  "embd_pdrop": 0.0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "mixformer-sequential",
+  "n_embd": 2048,
+  "n_head": 32,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.32.1",
+  "vocab_size": 51200,
+  "pad_vocab_size_multiple": 64
+}

puffin-phi-v2.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "microsoft/phi-1_5",
+  "activation_function": "gelu",
+  "architecture": {
+    "block_cls": "parallel",
+    "mixer": {},
+    "mlp": {
+      "mlp_cls": "mlp"
+    }
+  },
+  "architectures": [
+    "MixFormerSequentialForCausalLM"
+  ],
+  "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,
+  "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": "bfloat16",
+  "transformers_version": "4.34.0.dev0",
+  "use_cache": false,
+  "vocab_size": 50304,
+  "pad_vocab_size_multiple": 64
+}