Add 2-stage 1060k step model

config.json

@@ -11,6 +11,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 8640,
   "max_position_embeddings": 2048,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 26,
@@ -21,7 +22,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.38.0.dev0",
+  "transformers_version": "4.42.0.dev0",
   "use_cache": true,
   "vocab_size": 64256
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.38.0.dev0"
+  "transformers_version": "4.42.0.dev0"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:944f734c9d4facd84eb7b415f59bbd9c5463ccdf685b246fc08855c8cb5870b0
+oid sha256:ebea50b3d4ba830085a26f5a608edeaf36f78c3bc5b5c81c83ebec436576116c
 size 4953951976

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8115805319bd7f4bfc318984ab8651e8a5f1120a5548de36bb6244069d74eb2e
+oid sha256:0296bfe931223bd0ecb717a60bb9aea6ac40ab6c7e960f0a897eb9e8e2550c8b
 size 2311899224