Added bloom-7b1 model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +0,0 @@
----
-license: apache-2.0
----

config.json

@@ -0,0 +1,31 @@
+{
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 32,
+  "n_inner": null,
+  "n_layer": 30,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.22.2",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250880
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10df3a160ea5352261e667073a5a896fc0c5253a3ea31b78f7940fcff83ede07
+size 9976218536

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1ae1c8a2e7b30795c7741b8c1bedd1093ad87dd95e95614a1d78ad1c75f6d03
+size 4161852232

model.safetensors.index.json

@@ -0,0 +1,372 @@
+{
+    "metadata": {
+        "total_size": 14138032128
+    },
+    "weight_map": {
+        "h.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.0.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.0.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.0.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.0.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.0.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.0.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.1.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.1.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.1.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.1.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.1.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.1.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.10.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.10.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.10.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.10.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.10.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.10.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.11.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.11.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.11.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.11.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.11.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.11.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.12.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.12.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.12.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.12.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.12.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.12.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.13.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.13.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.13.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.13.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.13.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.13.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.14.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.14.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.14.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.14.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.14.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.14.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.14.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.14.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.15.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.15.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.15.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.15.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.15.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.15.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.15.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.15.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.16.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.16.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.16.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.16.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.16.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.16.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.16.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.16.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.16.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.17.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.17.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.17.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.17.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.17.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.17.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.17.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.17.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.17.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.18.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.18.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.18.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.18.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.18.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.18.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.18.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.18.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.18.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.19.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "h.19.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "h.19.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.19.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.19.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.19.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.19.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.19.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.19.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.2.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.2.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.2.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.2.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.2.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.2.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.20.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.20.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "h.20.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "h.20.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+        "h.20.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "h.20.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.20.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+        "h.20.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "h.20.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+        "h.20.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "h.21.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.21.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "h.21.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "h.21.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+        "h.21.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "h.21.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.21.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+        "h.21.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "h.21.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+        "h.21.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "h.22.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.22.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "h.22.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "h.22.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+        "h.22.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "h.22.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.22.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+        "h.22.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "h.22.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+        "h.22.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "h.23.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.23.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "h.23.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "h.23.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+        "h.23.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "h.23.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.23.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+        "h.23.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "h.23.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+        "h.23.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "h.24.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.24.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "h.24.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "h.24.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+        "h.24.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "h.24.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.24.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+        "h.24.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "h.24.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+        "h.24.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "h.25.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.25.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "h.25.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "h.25.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+        "h.25.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "h.25.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.25.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+        "h.25.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "h.25.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+        "h.25.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "h.26.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.26.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "h.26.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "h.26.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+        "h.26.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "h.26.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.26.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+        "h.26.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "h.26.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+        "h.26.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "h.27.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.27.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "h.27.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "h.27.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+        "h.27.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "h.27.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.27.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+        "h.27.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "h.27.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+        "h.27.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "h.28.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.28.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "h.28.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "h.28.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+        "h.28.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "h.28.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.28.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+        "h.28.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "h.28.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+        "h.28.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "h.29.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.29.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "h.29.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "h.29.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+        "h.29.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "h.29.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+        "h.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "h.29.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+        "h.29.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "h.29.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+        "h.29.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "h.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.3.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.3.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.3.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.3.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.3.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.3.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.4.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.4.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.4.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.4.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.4.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.4.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.5.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.5.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.5.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.5.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.5.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.5.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.6.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.6.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.6.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.6.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.6.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.6.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.7.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.7.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.7.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.7.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.7.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.7.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.8.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.8.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.8.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.8.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.8.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.8.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "h.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.9.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "h.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "h.9.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "h.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "h.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "h.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "h.9.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "h.9.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "h.9.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "h.9.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "ln_f.bias": "model-00002-of-00002.safetensors",
+        "ln_f.weight": "model-00002-of-00002.safetensors",
+        "word_embeddings.weight": "model-00001-of-00002.safetensors",
+        "word_embeddings_layernorm.bias": "model-00001-of-00002.safetensors",
+        "word_embeddings_layernorm.weight": "model-00001-of-00002.safetensors"
+    }
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f827f093c3e30875e96bc8093800f6fffcb81f8bd73e84109efcaae57f5d77ff
+size 9976268775

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a68540e3387c76ee41cc0e9c3ef8d73bd3ebcf00b7fbc3d689a70f583c7d70f1
+size 4161876233

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1b85a3b8b4190072590e8ca0e70086e209fd062698860a102a7df91c22cb5eb
+size 6005243331

pytorch_model.bin.index.json

@@ -0,0 +1,372 @@
+{
+  "metadata": {
+    "total_size": 14138032128
+  },
+  "weight_map": {
+    "h.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.0.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.1.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.10.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.10.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.11.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.11.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.11.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.11.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.12.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.12.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.12.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.12.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.12.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.13.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.13.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.13.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.13.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.13.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.14.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.14.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.14.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.14.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.14.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.15.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.15.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.15.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.15.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.15.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.15.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.16.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.16.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.16.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.16.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.16.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.16.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.17.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.17.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.17.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.17.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.17.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.17.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.18.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.18.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.18.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.18.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.18.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.18.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.19.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.19.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.19.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.19.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.19.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.19.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.19.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.2.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.20.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.20.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.20.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.20.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.20.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.20.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.20.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.21.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.21.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.21.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.21.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.21.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.21.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.22.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.22.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.22.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.22.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.22.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.22.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.22.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.23.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.23.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.23.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.23.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.23.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.24.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.24.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.24.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.24.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.24.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.24.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.24.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.25.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.25.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.25.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.25.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.25.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.25.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.25.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.26.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.26.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.26.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.26.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.26.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.26.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.26.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.27.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.27.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.27.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.27.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.27.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.27.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.27.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.28.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.28.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.28.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.28.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.28.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.28.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.28.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.29.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.29.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.29.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "h.29.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "h.29.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "h.29.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "h.29.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "h.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.3.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.4.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.4.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.5.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.5.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.6.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.6.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.7.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.7.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.8.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.8.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "h.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "h.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "h.9.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "h.9.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "h.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "ln_f.bias": "pytorch_model-00002-of-00002.bin",
+    "ln_f.weight": "pytorch_model-00002-of-00002.bin",
+    "word_embeddings.weight": "pytorch_model-00001-of-00002.bin",
+    "word_embeddings_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "word_embeddings_layernorm.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fa39cd4b1500feb205bcce3b9703a4373414cafe4970e0657b413f7ddd2a9d3
+size 14500438

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "eos_token": "</s>", "bos_token": "<s>", "pad_token": "<pad>", "name_or_path": "bigscience/tokenizer", "special_tokens_map_file": null, "tokenizer_class": "BloomTokenizerFast", "padding_side":"left"}