step 70128

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": ".",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 56,
+  "n_layer": 54,
+  "pad_token_id": 3,
+  "pretraining_tp": 2,
+  "slow_but_exact": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.33.0",
+  "use_cache": true,
+  "vocab_size": 128000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.33.0"
+}

pytorch_model-00001-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea7b34c5d10905d088adee170496022e19356119b8c061244f0ca8dd6a346f7e
+size 9646093541

pytorch_model-00002-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41c165ec9533b91e3c937c13a36764c88ee138e20305620bafc54c7b3e1337d5
+size 9866528411

pytorch_model-00003-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9934f122609e847c516043b957242335f51550aa744b6de847eaac5d1bfc3fa6
+size 9866528411

pytorch_model-00004-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01c530bf84ff6cb393969a7a43a711532233c46845c940cfef4fabaf505a5662
+size 9866528411

pytorch_model-00005-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b403b4d68f9c8ae70a8ea4f79da29b9d3d356473e60c3c42883bef8d0624e28
+size 9866528411

pytorch_model-00006-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48a1fa998cfe7ea43ae6723ab19558ea923e23f60ed6e49619f9919728ed53f3
+size 9866528411

pytorch_model-00007-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be5400fd439c68606aa90d1b658c22314a0f72abad38e197d397a99f2ee444fe
+size 9455398375

pytorch_model.bin.index.json

@@ -0,0 +1,661 @@
+{
+  "metadata": {
+    "total_size": 68433899520
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.self_attention.dense.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.self_attention.dense.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.10.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.10.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.10.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.10.self_attention.dense.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.10.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.10.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.11.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.11.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.11.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.11.self_attention.dense.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.11.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.11.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.12.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.12.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.12.self_attention.dense.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.12.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.12.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.13.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.13.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.13.self_attention.dense.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.13.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.13.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.14.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.14.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.14.self_attention.dense.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.14.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.14.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.15.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.15.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.15.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.15.self_attention.dense.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.15.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.15.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.16.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.16.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.16.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.16.self_attention.dense.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.16.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.16.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.17.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.17.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.17.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.17.self_attention.dense.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.17.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.17.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.18.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.18.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.18.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.18.self_attention.dense.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.18.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.18.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.19.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.19.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.19.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.19.self_attention.dense.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.19.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.19.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.2.input_layernorm.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.self_attention.dense.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.20.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.20.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.20.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.20.self_attention.dense.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.20.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.20.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.21.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.21.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.21.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.21.self_attention.dense.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.21.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.21.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.22.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.22.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.22.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.22.self_attention.dense.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.22.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.22.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
+    "transformer.h.23.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.23.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.23.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.23.self_attention.dense.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.23.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.23.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.24.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.24.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.24.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.24.self_attention.dense.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.24.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.24.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.25.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.25.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.25.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.25.self_attention.dense.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.25.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.25.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.26.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.26.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.26.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.26.self_attention.dense.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.26.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.26.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.27.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.27.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.27.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.27.self_attention.dense.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.27.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.27.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.28.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.28.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.28.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.28.self_attention.dense.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.28.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.28.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.29.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.29.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.29.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.29.self_attention.dense.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.29.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.29.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.3.input_layernorm.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.self_attention.dense.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.30.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.30.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.30.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.30.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.30.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.30.self_attention.dense.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.30.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.30.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
+    "transformer.h.31.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.31.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.31.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.31.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.31.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.31.self_attention.dense.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.31.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.31.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.32.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.32.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.32.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.32.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.32.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.32.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.32.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.32.self_attention.dense.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.32.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.32.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.32.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.33.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.33.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.33.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.33.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.33.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.33.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.33.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.33.self_attention.dense.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.33.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.33.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.33.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.34.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.34.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.34.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.34.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.34.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.34.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.34.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.34.self_attention.dense.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.34.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.34.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.34.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.35.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.35.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.35.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.35.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.35.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.35.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.35.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.35.self_attention.dense.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.35.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.35.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.35.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.36.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.36.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.36.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.36.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.36.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.36.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.36.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.36.self_attention.dense.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.36.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.36.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.36.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.37.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.37.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.37.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.37.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.37.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.37.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.37.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.37.self_attention.dense.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.37.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.37.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.37.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.38.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.38.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.38.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.38.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.38.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.38.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.38.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.38.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.38.self_attention.dense.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.38.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.38.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.38.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
+    "transformer.h.39.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.39.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.39.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.39.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.39.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.39.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.39.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.39.self_attention.dense.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.39.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.39.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.39.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.4.input_layernorm.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.4.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.4.self_attention.dense.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.4.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.4.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.40.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.40.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.40.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.40.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.40.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.40.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.40.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.40.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.40.self_attention.dense.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.40.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.40.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.40.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.41.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.41.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.41.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.41.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.41.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.41.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.41.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.41.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.41.self_attention.dense.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.41.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.41.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.41.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.42.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.42.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.42.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.42.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.42.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.42.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.42.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.42.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.42.self_attention.dense.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.42.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.42.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.42.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.43.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.43.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.43.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.43.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.43.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.43.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.43.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.43.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.43.self_attention.dense.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.43.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.43.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.43.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.44.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.44.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.44.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.44.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.44.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.44.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.44.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.44.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.44.self_attention.dense.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.44.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.44.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.44.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.45.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.45.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.45.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.45.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.45.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.45.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.45.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.45.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.45.self_attention.dense.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.45.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.45.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.45.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.46.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.46.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.46.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.46.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.46.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.46.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.46.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.46.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.46.self_attention.dense.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.46.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.46.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.46.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
+    "transformer.h.47.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.47.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.47.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.47.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.47.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.47.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.47.post_attention_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.47.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.47.self_attention.dense.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.47.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.47.self_attention.query_key_value.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.47.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.48.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.48.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.48.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.48.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.48.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.48.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.48.post_attention_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.48.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.48.self_attention.dense.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.48.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.48.self_attention.query_key_value.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.48.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.49.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.49.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.49.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.49.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.49.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.49.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.49.post_attention_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.49.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.49.self_attention.dense.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.49.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.49.self_attention.query_key_value.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.49.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.5.input_layernorm.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.5.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.5.self_attention.dense.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.5.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.5.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.50.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.50.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.50.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.50.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.50.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.50.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.50.post_attention_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.50.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.50.self_attention.dense.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.50.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.50.self_attention.query_key_value.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.50.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.51.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.51.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.51.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.51.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.51.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.51.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.51.post_attention_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.51.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.51.self_attention.dense.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.51.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.51.self_attention.query_key_value.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.51.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.52.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.52.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.52.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.52.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.52.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.52.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.52.post_attention_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.52.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.52.self_attention.dense.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.52.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.52.self_attention.query_key_value.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.52.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.53.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.53.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.53.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.53.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.53.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.53.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.53.post_attention_layernorm.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.53.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.53.self_attention.dense.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.53.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.53.self_attention.query_key_value.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.53.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.h.6.input_layernorm.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.6.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.6.self_attention.dense.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.6.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.6.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.h.7.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.self_attention.dense.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.self_attention.dense.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.9.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.9.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.9.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.9.self_attention.dense.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.9.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.9.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
+    "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
+    "transformer.ln_f.bias": "pytorch_model-00007-of-00007.bin",
+    "transformer.ln_f.weight": "pytorch_model-00007-of-00007.bin",
+    "transformer.word_embeddings.weight": "pytorch_model-00001-of-00007.bin",
+    "transformer.word_embeddings_layernorm.bias": "pytorch_model-00001-of-00007.bin",
+    "transformer.word_embeddings_layernorm.weight": "pytorch_model-00001-of-00007.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<|user|>",
+    "<|assistant|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>"
+}