init

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "togethercomputer/RedPajama-INCITE-Base-3B-v1",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 1.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.30.2",
+  "use_cache": true,
+  "use_parallel_residual": false,
+  "vocab_size": 50432
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.30.2"
+}

pytorch_model-00001-of-00012.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd22c92b18444f31c1dc252a1e3cd3d161278d34829fce46b2c020b23685c420
+size 944465940

pytorch_model-00002-of-00012.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb22a69724cf49176f813c51e034b7aa49f83d5a33bc87ade652c430734d507d
+size 956714526

pytorch_model-00003-of-00012.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cc5b6b72bc82e69c4c27098728e506473dd2144efa7a323df737f727fc8814d
+size 956714526

pytorch_model-00004-of-00012.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bac5eca161403deb6e56051bb10e9be07161af37d426051cd135b92463af3e23
+size 956714590

pytorch_model-00005-of-00012.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26feae368f7503c5394bb6011282a89c7a068be3e836b5a8f9e78091cbae5859
+size 956714590

pytorch_model-00006-of-00012.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:447b05a92fdc7451c2467e8b8941b537ec16de6efea60bd112a74fc0a971a6ea
+size 956714590

pytorch_model-00007-of-00012.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cd182dbbe62847da62f0141ee6345f17669186cfb90997e0cb9a60a13f63c0c
+size 956714590

pytorch_model-00008-of-00012.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e9364cf2c7eeee204de17f3d01908ae06aca367a1686fb2ae90343112bfddb9
+size 956714590

pytorch_model-00009-of-00012.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f05063f6e1cd6b5bde269a89947b789ea846ff12b67a8e3ba1a240687265639f
+size 956714590

pytorch_model-00010-of-00012.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9165af2ece5668e335315f7ee3f3d83f99957b8b63e34dc23290ee9be2ecde0a
+size 956714590

pytorch_model-00011-of-00012.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2a4f112c2c60ce248fc2c8c36dfa7d61e15f46da33d21b78445a4ea6c39dbfe
+size 956714590

pytorch_model-00012-of-00012.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca17ad27236b68aaed34e8fca5e12695dd7628b4ba0f76da1756ac0f785da771
+size 726212691

pytorch_model.bin.index.json

@@ -0,0 +1 @@
+{"weight_map": {"gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-1-of-33.bin", "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-1-of-33.bin", "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-1-of-33.bin", "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-1-of-33.bin", "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-1-of-33.bin", "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-1-of-33.bin", "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-1-of-33.bin", "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-1-of-33.bin", "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-1-of-33.bin", "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-1-of-33.bin", "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-1-of-33.bin", "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-1-of-33.bin", "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-2-of-33.bin", "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-2-of-33.bin", "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-2-of-33.bin", "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-2-of-33.bin", "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-2-of-33.bin", "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-2-of-33.bin", "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-2-of-33.bin", "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-2-of-33.bin", "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-2-of-33.bin", "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-2-of-33.bin", "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-2-of-33.bin", "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-2-of-33.bin", "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-3-of-33.bin", "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-3-of-33.bin", "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-3-of-33.bin", "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-3-of-33.bin", "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-3-of-33.bin", "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-3-of-33.bin", "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-3-of-33.bin", "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-3-of-33.bin", "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-3-of-33.bin", "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-3-of-33.bin", "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-3-of-33.bin", "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-3-of-33.bin", "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-4-of-33.bin", "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-4-of-33.bin", "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-4-of-33.bin", "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-4-of-33.bin", "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-4-of-33.bin", "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-4-of-33.bin", "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-4-of-33.bin", "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-4-of-33.bin", "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-4-of-33.bin", "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-4-of-33.bin", "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-4-of-33.bin", "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-4-of-33.bin", "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-5-of-33.bin", "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-5-of-33.bin", "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-5-of-33.bin", "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-5-of-33.bin", "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-5-of-33.bin", "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-5-of-33.bin", "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-5-of-33.bin", "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-5-of-33.bin", "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-5-of-33.bin", "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-5-of-33.bin", "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-5-of-33.bin", "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-5-of-33.bin", "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-6-of-33.bin", "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-6-of-33.bin", "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-6-of-33.bin", "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-6-of-33.bin", "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-6-of-33.bin", "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-6-of-33.bin", "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-6-of-33.bin", "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-6-of-33.bin", "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-6-of-33.bin", "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-6-of-33.bin", "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-6-of-33.bin", "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-6-of-33.bin", "gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-7-of-33.bin", "gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-7-of-33.bin", "gpt_neox.layers.6.attention.dense.weight": "pytorch_model-7-of-33.bin", "gpt_neox.layers.6.attention.dense.bias": "pytorch_model-7-of-33.bin", "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-7-of-33.bin", "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-7-of-33.bin", "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-7-of-33.bin", "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-7-of-33.bin", "gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-7-of-33.bin", "gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-7-of-33.bin", "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-7-of-33.bin", "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-7-of-33.bin", "gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-8-of-33.bin", "gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-8-of-33.bin", "gpt_neox.layers.7.attention.dense.weight": "pytorch_model-8-of-33.bin", "gpt_neox.layers.7.attention.dense.bias": "pytorch_model-8-of-33.bin", "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-8-of-33.bin", "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-8-of-33.bin", "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-8-of-33.bin", "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-8-of-33.bin", "gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-8-of-33.bin", "gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-8-of-33.bin", "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-8-of-33.bin", "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-8-of-33.bin", "gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-9-of-33.bin", "gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-9-of-33.bin", "gpt_neox.layers.8.attention.dense.weight": "pytorch_model-9-of-33.bin", "gpt_neox.layers.8.attention.dense.bias": "pytorch_model-9-of-33.bin", "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-9-of-33.bin", "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-9-of-33.bin", "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-9-of-33.bin", "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-9-of-33.bin", "gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-9-of-33.bin", "gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-9-of-33.bin", "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-9-of-33.bin", "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-9-of-33.bin", "gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-10-of-33.bin", "gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-10-of-33.bin", "gpt_neox.layers.9.attention.dense.weight": "pytorch_model-10-of-33.bin", "gpt_neox.layers.9.attention.dense.bias": "pytorch_model-10-of-33.bin", "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-10-of-33.bin", "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-10-of-33.bin", "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-10-of-33.bin", "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-10-of-33.bin", "gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-10-of-33.bin", "gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-10-of-33.bin", "gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-10-of-33.bin", "gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-10-of-33.bin", "gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-11-of-33.bin", "gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-11-of-33.bin", "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-11-of-33.bin", "gpt_neox.layers.10.attention.dense.bias": "pytorch_model-11-of-33.bin", "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-11-of-33.bin", "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-11-of-33.bin", "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-11-of-33.bin", "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-11-of-33.bin", "gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-11-of-33.bin", "gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-11-of-33.bin", "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-11-of-33.bin", "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-11-of-33.bin", "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-12-of-33.bin", "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-12-of-33.bin", "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-12-of-33.bin", "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-12-of-33.bin", "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-12-of-33.bin", "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-12-of-33.bin", "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-12-of-33.bin", "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-12-of-33.bin", "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-12-of-33.bin", "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-12-of-33.bin", "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-12-of-33.bin", "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-12-of-33.bin", "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-13-of-33.bin", "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-13-of-33.bin", "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-13-of-33.bin", "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-13-of-33.bin", "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-13-of-33.bin", "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-13-of-33.bin", "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-13-of-33.bin", "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-13-of-33.bin", "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-13-of-33.bin", "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-13-of-33.bin", "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-13-of-33.bin", "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-13-of-33.bin", "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-14-of-33.bin", "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-14-of-33.bin", "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-14-of-33.bin", "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-14-of-33.bin", "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-14-of-33.bin", "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-14-of-33.bin", "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-14-of-33.bin", "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-14-of-33.bin", "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-14-of-33.bin", "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-14-of-33.bin", "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-14-of-33.bin", "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-14-of-33.bin", "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-15-of-33.bin", "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-15-of-33.bin", "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-15-of-33.bin", "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-15-of-33.bin", "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-15-of-33.bin", "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-15-of-33.bin", "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-15-of-33.bin", "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-15-of-33.bin", "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-15-of-33.bin", "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-15-of-33.bin", "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-15-of-33.bin", "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-15-of-33.bin", "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-16-of-33.bin", "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-16-of-33.bin", "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-16-of-33.bin", "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-16-of-33.bin", "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-16-of-33.bin", "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-16-of-33.bin", "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-16-of-33.bin", "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-16-of-33.bin", "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-16-of-33.bin", "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-16-of-33.bin", "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-16-of-33.bin", "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-16-of-33.bin", "gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-17-of-33.bin", "gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-17-of-33.bin", "gpt_neox.layers.16.attention.dense.weight": "pytorch_model-17-of-33.bin", "gpt_neox.layers.16.attention.dense.bias": "pytorch_model-17-of-33.bin", "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-17-of-33.bin", "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-17-of-33.bin", "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-17-of-33.bin", "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-17-of-33.bin", "gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-17-of-33.bin", "gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-17-of-33.bin", "gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-17-of-33.bin", "gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-17-of-33.bin", "gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-18-of-33.bin", "gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-18-of-33.bin", "gpt_neox.layers.17.attention.dense.weight": "pytorch_model-18-of-33.bin", "gpt_neox.layers.17.attention.dense.bias": "pytorch_model-18-of-33.bin", "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-18-of-33.bin", "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-18-of-33.bin", "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-18-of-33.bin", "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-18-of-33.bin", "gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-18-of-33.bin", "gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-18-of-33.bin", "gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-18-of-33.bin", "gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-18-of-33.bin", "gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-19-of-33.bin", "gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-19-of-33.bin", "gpt_neox.layers.18.attention.dense.weight": "pytorch_model-19-of-33.bin", "gpt_neox.layers.18.attention.dense.bias": "pytorch_model-19-of-33.bin", "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-19-of-33.bin", "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-19-of-33.bin", "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-19-of-33.bin", "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-19-of-33.bin", "gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-19-of-33.bin", "gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-19-of-33.bin", "gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-19-of-33.bin", "gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-19-of-33.bin", "gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-20-of-33.bin", "gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-20-of-33.bin", "gpt_neox.layers.19.attention.dense.weight": "pytorch_model-20-of-33.bin", "gpt_neox.layers.19.attention.dense.bias": "pytorch_model-20-of-33.bin", "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-20-of-33.bin", "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-20-of-33.bin", "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-20-of-33.bin", "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-20-of-33.bin", "gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-20-of-33.bin", "gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-20-of-33.bin", "gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-20-of-33.bin", "gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-20-of-33.bin", "gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-21-of-33.bin", "gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-21-of-33.bin", "gpt_neox.layers.20.attention.dense.weight": "pytorch_model-21-of-33.bin", "gpt_neox.layers.20.attention.dense.bias": "pytorch_model-21-of-33.bin", "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-21-of-33.bin", "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-21-of-33.bin", "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-21-of-33.bin", "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-21-of-33.bin", "gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-21-of-33.bin", "gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-21-of-33.bin", "gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-21-of-33.bin", "gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-21-of-33.bin", "gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-22-of-33.bin", "gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-22-of-33.bin", "gpt_neox.layers.21.attention.dense.weight": "pytorch_model-22-of-33.bin", "gpt_neox.layers.21.attention.dense.bias": "pytorch_model-22-of-33.bin", "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-22-of-33.bin", "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-22-of-33.bin", "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-22-of-33.bin", "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-22-of-33.bin", "gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-22-of-33.bin", "gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-22-of-33.bin", "gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-22-of-33.bin", "gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-22-of-33.bin", "gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-23-of-33.bin", "gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-23-of-33.bin", "gpt_neox.layers.22.attention.dense.weight": "pytorch_model-23-of-33.bin", "gpt_neox.layers.22.attention.dense.bias": "pytorch_model-23-of-33.bin", "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-23-of-33.bin", "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-23-of-33.bin", "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-23-of-33.bin", "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-23-of-33.bin", "gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-23-of-33.bin", "gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-23-of-33.bin", "gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-23-of-33.bin", "gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-23-of-33.bin", "gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-24-of-33.bin", "gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-24-of-33.bin", "gpt_neox.layers.23.attention.dense.weight": "pytorch_model-24-of-33.bin", "gpt_neox.layers.23.attention.dense.bias": "pytorch_model-24-of-33.bin", "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-24-of-33.bin", "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-24-of-33.bin", "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-24-of-33.bin", "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-24-of-33.bin", "gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-24-of-33.bin", "gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-24-of-33.bin", "gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-24-of-33.bin", "gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-24-of-33.bin", "gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-25-of-33.bin", "gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-25-of-33.bin", "gpt_neox.layers.24.attention.dense.weight": "pytorch_model-25-of-33.bin", "gpt_neox.layers.24.attention.dense.bias": "pytorch_model-25-of-33.bin", "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-25-of-33.bin", "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-25-of-33.bin", "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-25-of-33.bin", "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-25-of-33.bin", "gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-25-of-33.bin", "gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-25-of-33.bin", "gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-25-of-33.bin", "gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-25-of-33.bin", "gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-26-of-33.bin", "gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-26-of-33.bin", "gpt_neox.layers.25.attention.dense.weight": "pytorch_model-26-of-33.bin", "gpt_neox.layers.25.attention.dense.bias": "pytorch_model-26-of-33.bin", "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-26-of-33.bin", "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-26-of-33.bin", "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-26-of-33.bin", "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-26-of-33.bin", "gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-26-of-33.bin", "gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-26-of-33.bin", "gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-26-of-33.bin", "gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-26-of-33.bin", "gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-27-of-33.bin", "gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-27-of-33.bin", "gpt_neox.layers.26.attention.dense.weight": "pytorch_model-27-of-33.bin", "gpt_neox.layers.26.attention.dense.bias": "pytorch_model-27-of-33.bin", "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-27-of-33.bin", "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-27-of-33.bin", "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-27-of-33.bin", "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-27-of-33.bin", "gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-27-of-33.bin", "gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-27-of-33.bin", "gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-27-of-33.bin", "gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-27-of-33.bin", "gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-28-of-33.bin", "gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-28-of-33.bin", "gpt_neox.layers.27.attention.dense.weight": "pytorch_model-28-of-33.bin", "gpt_neox.layers.27.attention.dense.bias": "pytorch_model-28-of-33.bin", "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-28-of-33.bin", "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-28-of-33.bin", "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-28-of-33.bin", "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-28-of-33.bin", "gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-28-of-33.bin", "gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-28-of-33.bin", "gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-28-of-33.bin", "gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-28-of-33.bin", "gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-29-of-33.bin", "gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-29-of-33.bin", "gpt_neox.layers.28.attention.dense.weight": "pytorch_model-29-of-33.bin", "gpt_neox.layers.28.attention.dense.bias": "pytorch_model-29-of-33.bin", "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-29-of-33.bin", "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-29-of-33.bin", "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-29-of-33.bin", "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-29-of-33.bin", "gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-29-of-33.bin", "gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-29-of-33.bin", "gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-29-of-33.bin", "gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-29-of-33.bin", "gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-30-of-33.bin", "gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-30-of-33.bin", "gpt_neox.layers.29.attention.dense.weight": "pytorch_model-30-of-33.bin", "gpt_neox.layers.29.attention.dense.bias": "pytorch_model-30-of-33.bin", "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-30-of-33.bin", "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-30-of-33.bin", "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-30-of-33.bin", "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-30-of-33.bin", "gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-30-of-33.bin", "gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-30-of-33.bin", "gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-30-of-33.bin", "gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-30-of-33.bin", "gpt_neox.layers.30.attention.query_key_value.weight": "pytorch_model-31-of-33.bin", "gpt_neox.layers.30.attention.query_key_value.bias": "pytorch_model-31-of-33.bin", "gpt_neox.layers.30.attention.dense.weight": "pytorch_model-31-of-33.bin", "gpt_neox.layers.30.attention.dense.bias": "pytorch_model-31-of-33.bin", "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-31-of-33.bin", "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-31-of-33.bin", "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-31-of-33.bin", "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-31-of-33.bin", "gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-31-of-33.bin", "gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-31-of-33.bin", "gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-31-of-33.bin", "gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-31-of-33.bin", "gpt_neox.layers.31.attention.query_key_value.weight": "pytorch_model-32-of-33.bin", "gpt_neox.layers.31.attention.query_key_value.bias": "pytorch_model-32-of-33.bin", "gpt_neox.layers.31.attention.dense.weight": "pytorch_model-32-of-33.bin", "gpt_neox.layers.31.attention.dense.bias": "pytorch_model-32-of-33.bin", "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-32-of-33.bin", "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-32-of-33.bin", "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-32-of-33.bin", "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-32-of-33.bin", "gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-32-of-33.bin", "gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-32-of-33.bin", "gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-32-of-33.bin", "gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-32-of-33.bin", "gpt_neox.embed_in.weight": "pytorch_model-33-of-33.bin", "gpt_neox.final_layer_norm.weight": "pytorch_model-33-of-33.bin", "gpt_neox.final_layer_norm.bias": "pytorch_model-33-of-33.bin", "embed_out.weight": "pytorch_model-33-of-33.bin"}, "metadata": {"total_size": 5551728640}}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}