Add

.gitattributes

@@ -32,3 +32,4 @@ 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

config.json

@@ -0,0 +1,31 @@
+{
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomModel"
+  ],
+  "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,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_embed": 4096,
+  "n_inner": null,
+  "n_layer": 30,
+  "num_attention_heads": 32,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 4,
+  "seq_length": 2048,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "transformers_version": "4.21.0.dev0",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250880
+}

pytorch_model.bin.index.json

@@ -0,0 +1,372 @@
+{
+  "metadata": {
+    "total_size": 14138032128
+  },
+  "weight_map": {
+    "h.0.input_layernorm.bias": "pytorch_model_00002-of-00032.bin",
+    "h.0.input_layernorm.weight": "pytorch_model_00002-of-00032.bin",
+    "h.0.mlp.dense_4h_to_h.bias": "pytorch_model_00002-of-00032.bin",
+    "h.0.mlp.dense_4h_to_h.weight": "pytorch_model_00002-of-00032.bin",
+    "h.0.mlp.dense_h_to_4h.bias": "pytorch_model_00002-of-00032.bin",
+    "h.0.mlp.dense_h_to_4h.weight": "pytorch_model_00002-of-00032.bin",
+    "h.0.post_attention_layernorm.bias": "pytorch_model_00002-of-00032.bin",
+    "h.0.post_attention_layernorm.weight": "pytorch_model_00002-of-00032.bin",
+    "h.0.self_attention.dense.bias": "pytorch_model_00002-of-00032.bin",
+    "h.0.self_attention.dense.weight": "pytorch_model_00002-of-00032.bin",
+    "h.0.self_attention.query_key_value.bias": "pytorch_model_00002-of-00032.bin",
+    "h.0.self_attention.query_key_value.weight": "pytorch_model_00002-of-00032.bin",
+    "h.1.input_layernorm.bias": "pytorch_model_00003-of-00032.bin",
+    "h.1.input_layernorm.weight": "pytorch_model_00003-of-00032.bin",
+    "h.1.mlp.dense_4h_to_h.bias": "pytorch_model_00003-of-00032.bin",
+    "h.1.mlp.dense_4h_to_h.weight": "pytorch_model_00003-of-00032.bin",
+    "h.1.mlp.dense_h_to_4h.bias": "pytorch_model_00003-of-00032.bin",
+    "h.1.mlp.dense_h_to_4h.weight": "pytorch_model_00003-of-00032.bin",
+    "h.1.post_attention_layernorm.bias": "pytorch_model_00003-of-00032.bin",
+    "h.1.post_attention_layernorm.weight": "pytorch_model_00003-of-00032.bin",
+    "h.1.self_attention.dense.bias": "pytorch_model_00003-of-00032.bin",
+    "h.1.self_attention.dense.weight": "pytorch_model_00003-of-00032.bin",
+    "h.1.self_attention.query_key_value.bias": "pytorch_model_00003-of-00032.bin",
+    "h.1.self_attention.query_key_value.weight": "pytorch_model_00003-of-00032.bin",
+    "h.10.input_layernorm.bias": "pytorch_model_00012-of-00032.bin",
+    "h.10.input_layernorm.weight": "pytorch_model_00012-of-00032.bin",
+    "h.10.mlp.dense_4h_to_h.bias": "pytorch_model_00012-of-00032.bin",
+    "h.10.mlp.dense_4h_to_h.weight": "pytorch_model_00012-of-00032.bin",
+    "h.10.mlp.dense_h_to_4h.bias": "pytorch_model_00012-of-00032.bin",
+    "h.10.mlp.dense_h_to_4h.weight": "pytorch_model_00012-of-00032.bin",
+    "h.10.post_attention_layernorm.bias": "pytorch_model_00012-of-00032.bin",
+    "h.10.post_attention_layernorm.weight": "pytorch_model_00012-of-00032.bin",
+    "h.10.self_attention.dense.bias": "pytorch_model_00012-of-00032.bin",
+    "h.10.self_attention.dense.weight": "pytorch_model_00012-of-00032.bin",
+    "h.10.self_attention.query_key_value.bias": "pytorch_model_00012-of-00032.bin",
+    "h.10.self_attention.query_key_value.weight": "pytorch_model_00012-of-00032.bin",
+    "h.11.input_layernorm.bias": "pytorch_model_00013-of-00032.bin",
+    "h.11.input_layernorm.weight": "pytorch_model_00013-of-00032.bin",
+    "h.11.mlp.dense_4h_to_h.bias": "pytorch_model_00013-of-00032.bin",
+    "h.11.mlp.dense_4h_to_h.weight": "pytorch_model_00013-of-00032.bin",
+    "h.11.mlp.dense_h_to_4h.bias": "pytorch_model_00013-of-00032.bin",
+    "h.11.mlp.dense_h_to_4h.weight": "pytorch_model_00013-of-00032.bin",
+    "h.11.post_attention_layernorm.bias": "pytorch_model_00013-of-00032.bin",
+    "h.11.post_attention_layernorm.weight": "pytorch_model_00013-of-00032.bin",
+    "h.11.self_attention.dense.bias": "pytorch_model_00013-of-00032.bin",
+    "h.11.self_attention.dense.weight": "pytorch_model_00013-of-00032.bin",
+    "h.11.self_attention.query_key_value.bias": "pytorch_model_00013-of-00032.bin",
+    "h.11.self_attention.query_key_value.weight": "pytorch_model_00013-of-00032.bin",
+    "h.12.input_layernorm.bias": "pytorch_model_00014-of-00032.bin",
+    "h.12.input_layernorm.weight": "pytorch_model_00014-of-00032.bin",
+    "h.12.mlp.dense_4h_to_h.bias": "pytorch_model_00014-of-00032.bin",
+    "h.12.mlp.dense_4h_to_h.weight": "pytorch_model_00014-of-00032.bin",
+    "h.12.mlp.dense_h_to_4h.bias": "pytorch_model_00014-of-00032.bin",
+    "h.12.mlp.dense_h_to_4h.weight": "pytorch_model_00014-of-00032.bin",
+    "h.12.post_attention_layernorm.bias": "pytorch_model_00014-of-00032.bin",
+    "h.12.post_attention_layernorm.weight": "pytorch_model_00014-of-00032.bin",
+    "h.12.self_attention.dense.bias": "pytorch_model_00014-of-00032.bin",
+    "h.12.self_attention.dense.weight": "pytorch_model_00014-of-00032.bin",
+    "h.12.self_attention.query_key_value.bias": "pytorch_model_00014-of-00032.bin",
+    "h.12.self_attention.query_key_value.weight": "pytorch_model_00014-of-00032.bin",
+    "h.13.input_layernorm.bias": "pytorch_model_00015-of-00032.bin",
+    "h.13.input_layernorm.weight": "pytorch_model_00015-of-00032.bin",
+    "h.13.mlp.dense_4h_to_h.bias": "pytorch_model_00015-of-00032.bin",
+    "h.13.mlp.dense_4h_to_h.weight": "pytorch_model_00015-of-00032.bin",
+    "h.13.mlp.dense_h_to_4h.bias": "pytorch_model_00015-of-00032.bin",
+    "h.13.mlp.dense_h_to_4h.weight": "pytorch_model_00015-of-00032.bin",
+    "h.13.post_attention_layernorm.bias": "pytorch_model_00015-of-00032.bin",
+    "h.13.post_attention_layernorm.weight": "pytorch_model_00015-of-00032.bin",
+    "h.13.self_attention.dense.bias": "pytorch_model_00015-of-00032.bin",
+    "h.13.self_attention.dense.weight": "pytorch_model_00015-of-00032.bin",
+    "h.13.self_attention.query_key_value.bias": "pytorch_model_00015-of-00032.bin",
+    "h.13.self_attention.query_key_value.weight": "pytorch_model_00015-of-00032.bin",
+    "h.14.input_layernorm.bias": "pytorch_model_00016-of-00032.bin",
+    "h.14.input_layernorm.weight": "pytorch_model_00016-of-00032.bin",
+    "h.14.mlp.dense_4h_to_h.bias": "pytorch_model_00016-of-00032.bin",
+    "h.14.mlp.dense_4h_to_h.weight": "pytorch_model_00016-of-00032.bin",
+    "h.14.mlp.dense_h_to_4h.bias": "pytorch_model_00016-of-00032.bin",
+    "h.14.mlp.dense_h_to_4h.weight": "pytorch_model_00016-of-00032.bin",
+    "h.14.post_attention_layernorm.bias": "pytorch_model_00016-of-00032.bin",
+    "h.14.post_attention_layernorm.weight": "pytorch_model_00016-of-00032.bin",
+    "h.14.self_attention.dense.bias": "pytorch_model_00016-of-00032.bin",
+    "h.14.self_attention.dense.weight": "pytorch_model_00016-of-00032.bin",
+    "h.14.self_attention.query_key_value.bias": "pytorch_model_00016-of-00032.bin",
+    "h.14.self_attention.query_key_value.weight": "pytorch_model_00016-of-00032.bin",
+    "h.15.input_layernorm.bias": "pytorch_model_00017-of-00032.bin",
+    "h.15.input_layernorm.weight": "pytorch_model_00017-of-00032.bin",
+    "h.15.mlp.dense_4h_to_h.bias": "pytorch_model_00017-of-00032.bin",
+    "h.15.mlp.dense_4h_to_h.weight": "pytorch_model_00017-of-00032.bin",
+    "h.15.mlp.dense_h_to_4h.bias": "pytorch_model_00017-of-00032.bin",
+    "h.15.mlp.dense_h_to_4h.weight": "pytorch_model_00017-of-00032.bin",
+    "h.15.post_attention_layernorm.bias": "pytorch_model_00017-of-00032.bin",
+    "h.15.post_attention_layernorm.weight": "pytorch_model_00017-of-00032.bin",
+    "h.15.self_attention.dense.bias": "pytorch_model_00017-of-00032.bin",
+    "h.15.self_attention.dense.weight": "pytorch_model_00017-of-00032.bin",
+    "h.15.self_attention.query_key_value.bias": "pytorch_model_00017-of-00032.bin",
+    "h.15.self_attention.query_key_value.weight": "pytorch_model_00017-of-00032.bin",
+    "h.16.input_layernorm.bias": "pytorch_model_00018-of-00032.bin",
+    "h.16.input_layernorm.weight": "pytorch_model_00018-of-00032.bin",
+    "h.16.mlp.dense_4h_to_h.bias": "pytorch_model_00018-of-00032.bin",
+    "h.16.mlp.dense_4h_to_h.weight": "pytorch_model_00018-of-00032.bin",
+    "h.16.mlp.dense_h_to_4h.bias": "pytorch_model_00018-of-00032.bin",
+    "h.16.mlp.dense_h_to_4h.weight": "pytorch_model_00018-of-00032.bin",
+    "h.16.post_attention_layernorm.bias": "pytorch_model_00018-of-00032.bin",
+    "h.16.post_attention_layernorm.weight": "pytorch_model_00018-of-00032.bin",
+    "h.16.self_attention.dense.bias": "pytorch_model_00018-of-00032.bin",
+    "h.16.self_attention.dense.weight": "pytorch_model_00018-of-00032.bin",
+    "h.16.self_attention.query_key_value.bias": "pytorch_model_00018-of-00032.bin",
+    "h.16.self_attention.query_key_value.weight": "pytorch_model_00018-of-00032.bin",
+    "h.17.input_layernorm.bias": "pytorch_model_00019-of-00032.bin",
+    "h.17.input_layernorm.weight": "pytorch_model_00019-of-00032.bin",
+    "h.17.mlp.dense_4h_to_h.bias": "pytorch_model_00019-of-00032.bin",
+    "h.17.mlp.dense_4h_to_h.weight": "pytorch_model_00019-of-00032.bin",
+    "h.17.mlp.dense_h_to_4h.bias": "pytorch_model_00019-of-00032.bin",
+    "h.17.mlp.dense_h_to_4h.weight": "pytorch_model_00019-of-00032.bin",
+    "h.17.post_attention_layernorm.bias": "pytorch_model_00019-of-00032.bin",
+    "h.17.post_attention_layernorm.weight": "pytorch_model_00019-of-00032.bin",
+    "h.17.self_attention.dense.bias": "pytorch_model_00019-of-00032.bin",
+    "h.17.self_attention.dense.weight": "pytorch_model_00019-of-00032.bin",
+    "h.17.self_attention.query_key_value.bias": "pytorch_model_00019-of-00032.bin",
+    "h.17.self_attention.query_key_value.weight": "pytorch_model_00019-of-00032.bin",
+    "h.18.input_layernorm.bias": "pytorch_model_00020-of-00032.bin",
+    "h.18.input_layernorm.weight": "pytorch_model_00020-of-00032.bin",
+    "h.18.mlp.dense_4h_to_h.bias": "pytorch_model_00020-of-00032.bin",
+    "h.18.mlp.dense_4h_to_h.weight": "pytorch_model_00020-of-00032.bin",
+    "h.18.mlp.dense_h_to_4h.bias": "pytorch_model_00020-of-00032.bin",
+    "h.18.mlp.dense_h_to_4h.weight": "pytorch_model_00020-of-00032.bin",
+    "h.18.post_attention_layernorm.bias": "pytorch_model_00020-of-00032.bin",
+    "h.18.post_attention_layernorm.weight": "pytorch_model_00020-of-00032.bin",
+    "h.18.self_attention.dense.bias": "pytorch_model_00020-of-00032.bin",
+    "h.18.self_attention.dense.weight": "pytorch_model_00020-of-00032.bin",
+    "h.18.self_attention.query_key_value.bias": "pytorch_model_00020-of-00032.bin",
+    "h.18.self_attention.query_key_value.weight": "pytorch_model_00020-of-00032.bin",
+    "h.19.input_layernorm.bias": "pytorch_model_00021-of-00032.bin",
+    "h.19.input_layernorm.weight": "pytorch_model_00021-of-00032.bin",
+    "h.19.mlp.dense_4h_to_h.bias": "pytorch_model_00021-of-00032.bin",
+    "h.19.mlp.dense_4h_to_h.weight": "pytorch_model_00021-of-00032.bin",
+    "h.19.mlp.dense_h_to_4h.bias": "pytorch_model_00021-of-00032.bin",
+    "h.19.mlp.dense_h_to_4h.weight": "pytorch_model_00021-of-00032.bin",
+    "h.19.post_attention_layernorm.bias": "pytorch_model_00021-of-00032.bin",
+    "h.19.post_attention_layernorm.weight": "pytorch_model_00021-of-00032.bin",
+    "h.19.self_attention.dense.bias": "pytorch_model_00021-of-00032.bin",
+    "h.19.self_attention.dense.weight": "pytorch_model_00021-of-00032.bin",
+    "h.19.self_attention.query_key_value.bias": "pytorch_model_00021-of-00032.bin",
+    "h.19.self_attention.query_key_value.weight": "pytorch_model_00021-of-00032.bin",
+    "h.2.input_layernorm.bias": "pytorch_model_00004-of-00032.bin",
+    "h.2.input_layernorm.weight": "pytorch_model_00004-of-00032.bin",
+    "h.2.mlp.dense_4h_to_h.bias": "pytorch_model_00004-of-00032.bin",
+    "h.2.mlp.dense_4h_to_h.weight": "pytorch_model_00004-of-00032.bin",
+    "h.2.mlp.dense_h_to_4h.bias": "pytorch_model_00004-of-00032.bin",
+    "h.2.mlp.dense_h_to_4h.weight": "pytorch_model_00004-of-00032.bin",
+    "h.2.post_attention_layernorm.bias": "pytorch_model_00004-of-00032.bin",
+    "h.2.post_attention_layernorm.weight": "pytorch_model_00004-of-00032.bin",
+    "h.2.self_attention.dense.bias": "pytorch_model_00004-of-00032.bin",
+    "h.2.self_attention.dense.weight": "pytorch_model_00004-of-00032.bin",
+    "h.2.self_attention.query_key_value.bias": "pytorch_model_00004-of-00032.bin",
+    "h.2.self_attention.query_key_value.weight": "pytorch_model_00004-of-00032.bin",
+    "h.20.input_layernorm.bias": "pytorch_model_00022-of-00032.bin",
+    "h.20.input_layernorm.weight": "pytorch_model_00022-of-00032.bin",
+    "h.20.mlp.dense_4h_to_h.bias": "pytorch_model_00022-of-00032.bin",
+    "h.20.mlp.dense_4h_to_h.weight": "pytorch_model_00022-of-00032.bin",
+    "h.20.mlp.dense_h_to_4h.bias": "pytorch_model_00022-of-00032.bin",
+    "h.20.mlp.dense_h_to_4h.weight": "pytorch_model_00022-of-00032.bin",
+    "h.20.post_attention_layernorm.bias": "pytorch_model_00022-of-00032.bin",
+    "h.20.post_attention_layernorm.weight": "pytorch_model_00022-of-00032.bin",
+    "h.20.self_attention.dense.bias": "pytorch_model_00022-of-00032.bin",
+    "h.20.self_attention.dense.weight": "pytorch_model_00022-of-00032.bin",
+    "h.20.self_attention.query_key_value.bias": "pytorch_model_00022-of-00032.bin",
+    "h.20.self_attention.query_key_value.weight": "pytorch_model_00022-of-00032.bin",
+    "h.21.input_layernorm.bias": "pytorch_model_00023-of-00032.bin",
+    "h.21.input_layernorm.weight": "pytorch_model_00023-of-00032.bin",
+    "h.21.mlp.dense_4h_to_h.bias": "pytorch_model_00023-of-00032.bin",
+    "h.21.mlp.dense_4h_to_h.weight": "pytorch_model_00023-of-00032.bin",
+    "h.21.mlp.dense_h_to_4h.bias": "pytorch_model_00023-of-00032.bin",
+    "h.21.mlp.dense_h_to_4h.weight": "pytorch_model_00023-of-00032.bin",
+    "h.21.post_attention_layernorm.bias": "pytorch_model_00023-of-00032.bin",
+    "h.21.post_attention_layernorm.weight": "pytorch_model_00023-of-00032.bin",
+    "h.21.self_attention.dense.bias": "pytorch_model_00023-of-00032.bin",
+    "h.21.self_attention.dense.weight": "pytorch_model_00023-of-00032.bin",
+    "h.21.self_attention.query_key_value.bias": "pytorch_model_00023-of-00032.bin",
+    "h.21.self_attention.query_key_value.weight": "pytorch_model_00023-of-00032.bin",
+    "h.22.input_layernorm.bias": "pytorch_model_00024-of-00032.bin",
+    "h.22.input_layernorm.weight": "pytorch_model_00024-of-00032.bin",
+    "h.22.mlp.dense_4h_to_h.bias": "pytorch_model_00024-of-00032.bin",
+    "h.22.mlp.dense_4h_to_h.weight": "pytorch_model_00024-of-00032.bin",
+    "h.22.mlp.dense_h_to_4h.bias": "pytorch_model_00024-of-00032.bin",
+    "h.22.mlp.dense_h_to_4h.weight": "pytorch_model_00024-of-00032.bin",
+    "h.22.post_attention_layernorm.bias": "pytorch_model_00024-of-00032.bin",
+    "h.22.post_attention_layernorm.weight": "pytorch_model_00024-of-00032.bin",
+    "h.22.self_attention.dense.bias": "pytorch_model_00024-of-00032.bin",
+    "h.22.self_attention.dense.weight": "pytorch_model_00024-of-00032.bin",
+    "h.22.self_attention.query_key_value.bias": "pytorch_model_00024-of-00032.bin",
+    "h.22.self_attention.query_key_value.weight": "pytorch_model_00024-of-00032.bin",
+    "h.23.input_layernorm.bias": "pytorch_model_00025-of-00032.bin",
+    "h.23.input_layernorm.weight": "pytorch_model_00025-of-00032.bin",
+    "h.23.mlp.dense_4h_to_h.bias": "pytorch_model_00025-of-00032.bin",
+    "h.23.mlp.dense_4h_to_h.weight": "pytorch_model_00025-of-00032.bin",
+    "h.23.mlp.dense_h_to_4h.bias": "pytorch_model_00025-of-00032.bin",
+    "h.23.mlp.dense_h_to_4h.weight": "pytorch_model_00025-of-00032.bin",
+    "h.23.post_attention_layernorm.bias": "pytorch_model_00025-of-00032.bin",
+    "h.23.post_attention_layernorm.weight": "pytorch_model_00025-of-00032.bin",
+    "h.23.self_attention.dense.bias": "pytorch_model_00025-of-00032.bin",
+    "h.23.self_attention.dense.weight": "pytorch_model_00025-of-00032.bin",
+    "h.23.self_attention.query_key_value.bias": "pytorch_model_00025-of-00032.bin",
+    "h.23.self_attention.query_key_value.weight": "pytorch_model_00025-of-00032.bin",
+    "h.24.input_layernorm.bias": "pytorch_model_00026-of-00032.bin",
+    "h.24.input_layernorm.weight": "pytorch_model_00026-of-00032.bin",
+    "h.24.mlp.dense_4h_to_h.bias": "pytorch_model_00026-of-00032.bin",
+    "h.24.mlp.dense_4h_to_h.weight": "pytorch_model_00026-of-00032.bin",
+    "h.24.mlp.dense_h_to_4h.bias": "pytorch_model_00026-of-00032.bin",
+    "h.24.mlp.dense_h_to_4h.weight": "pytorch_model_00026-of-00032.bin",
+    "h.24.post_attention_layernorm.bias": "pytorch_model_00026-of-00032.bin",
+    "h.24.post_attention_layernorm.weight": "pytorch_model_00026-of-00032.bin",
+    "h.24.self_attention.dense.bias": "pytorch_model_00026-of-00032.bin",
+    "h.24.self_attention.dense.weight": "pytorch_model_00026-of-00032.bin",
+    "h.24.self_attention.query_key_value.bias": "pytorch_model_00026-of-00032.bin",
+    "h.24.self_attention.query_key_value.weight": "pytorch_model_00026-of-00032.bin",
+    "h.25.input_layernorm.bias": "pytorch_model_00027-of-00032.bin",
+    "h.25.input_layernorm.weight": "pytorch_model_00027-of-00032.bin",
+    "h.25.mlp.dense_4h_to_h.bias": "pytorch_model_00027-of-00032.bin",
+    "h.25.mlp.dense_4h_to_h.weight": "pytorch_model_00027-of-00032.bin",
+    "h.25.mlp.dense_h_to_4h.bias": "pytorch_model_00027-of-00032.bin",
+    "h.25.mlp.dense_h_to_4h.weight": "pytorch_model_00027-of-00032.bin",
+    "h.25.post_attention_layernorm.bias": "pytorch_model_00027-of-00032.bin",
+    "h.25.post_attention_layernorm.weight": "pytorch_model_00027-of-00032.bin",
+    "h.25.self_attention.dense.bias": "pytorch_model_00027-of-00032.bin",
+    "h.25.self_attention.dense.weight": "pytorch_model_00027-of-00032.bin",
+    "h.25.self_attention.query_key_value.bias": "pytorch_model_00027-of-00032.bin",
+    "h.25.self_attention.query_key_value.weight": "pytorch_model_00027-of-00032.bin",
+    "h.26.input_layernorm.bias": "pytorch_model_00028-of-00032.bin",
+    "h.26.input_layernorm.weight": "pytorch_model_00028-of-00032.bin",
+    "h.26.mlp.dense_4h_to_h.bias": "pytorch_model_00028-of-00032.bin",
+    "h.26.mlp.dense_4h_to_h.weight": "pytorch_model_00028-of-00032.bin",
+    "h.26.mlp.dense_h_to_4h.bias": "pytorch_model_00028-of-00032.bin",
+    "h.26.mlp.dense_h_to_4h.weight": "pytorch_model_00028-of-00032.bin",
+    "h.26.post_attention_layernorm.bias": "pytorch_model_00028-of-00032.bin",
+    "h.26.post_attention_layernorm.weight": "pytorch_model_00028-of-00032.bin",
+    "h.26.self_attention.dense.bias": "pytorch_model_00028-of-00032.bin",
+    "h.26.self_attention.dense.weight": "pytorch_model_00028-of-00032.bin",
+    "h.26.self_attention.query_key_value.bias": "pytorch_model_00028-of-00032.bin",
+    "h.26.self_attention.query_key_value.weight": "pytorch_model_00028-of-00032.bin",
+    "h.27.input_layernorm.bias": "pytorch_model_00029-of-00032.bin",
+    "h.27.input_layernorm.weight": "pytorch_model_00029-of-00032.bin",
+    "h.27.mlp.dense_4h_to_h.bias": "pytorch_model_00029-of-00032.bin",
+    "h.27.mlp.dense_4h_to_h.weight": "pytorch_model_00029-of-00032.bin",
+    "h.27.mlp.dense_h_to_4h.bias": "pytorch_model_00029-of-00032.bin",
+    "h.27.mlp.dense_h_to_4h.weight": "pytorch_model_00029-of-00032.bin",
+    "h.27.post_attention_layernorm.bias": "pytorch_model_00029-of-00032.bin",
+    "h.27.post_attention_layernorm.weight": "pytorch_model_00029-of-00032.bin",
+    "h.27.self_attention.dense.bias": "pytorch_model_00029-of-00032.bin",
+    "h.27.self_attention.dense.weight": "pytorch_model_00029-of-00032.bin",
+    "h.27.self_attention.query_key_value.bias": "pytorch_model_00029-of-00032.bin",
+    "h.27.self_attention.query_key_value.weight": "pytorch_model_00029-of-00032.bin",
+    "h.28.input_layernorm.bias": "pytorch_model_00030-of-00032.bin",
+    "h.28.input_layernorm.weight": "pytorch_model_00030-of-00032.bin",
+    "h.28.mlp.dense_4h_to_h.bias": "pytorch_model_00030-of-00032.bin",
+    "h.28.mlp.dense_4h_to_h.weight": "pytorch_model_00030-of-00032.bin",
+    "h.28.mlp.dense_h_to_4h.bias": "pytorch_model_00030-of-00032.bin",
+    "h.28.mlp.dense_h_to_4h.weight": "pytorch_model_00030-of-00032.bin",
+    "h.28.post_attention_layernorm.bias": "pytorch_model_00030-of-00032.bin",
+    "h.28.post_attention_layernorm.weight": "pytorch_model_00030-of-00032.bin",
+    "h.28.self_attention.dense.bias": "pytorch_model_00030-of-00032.bin",
+    "h.28.self_attention.dense.weight": "pytorch_model_00030-of-00032.bin",
+    "h.28.self_attention.query_key_value.bias": "pytorch_model_00030-of-00032.bin",
+    "h.28.self_attention.query_key_value.weight": "pytorch_model_00030-of-00032.bin",
+    "h.29.input_layernorm.bias": "pytorch_model_00031-of-00032.bin",
+    "h.29.input_layernorm.weight": "pytorch_model_00031-of-00032.bin",
+    "h.29.mlp.dense_4h_to_h.bias": "pytorch_model_00031-of-00032.bin",
+    "h.29.mlp.dense_4h_to_h.weight": "pytorch_model_00031-of-00032.bin",
+    "h.29.mlp.dense_h_to_4h.bias": "pytorch_model_00031-of-00032.bin",
+    "h.29.mlp.dense_h_to_4h.weight": "pytorch_model_00031-of-00032.bin",
+    "h.29.post_attention_layernorm.bias": "pytorch_model_00031-of-00032.bin",
+    "h.29.post_attention_layernorm.weight": "pytorch_model_00031-of-00032.bin",
+    "h.29.self_attention.dense.bias": "pytorch_model_00031-of-00032.bin",
+    "h.29.self_attention.dense.weight": "pytorch_model_00031-of-00032.bin",
+    "h.29.self_attention.query_key_value.bias": "pytorch_model_00031-of-00032.bin",
+    "h.29.self_attention.query_key_value.weight": "pytorch_model_00031-of-00032.bin",
+    "h.3.input_layernorm.bias": "pytorch_model_00005-of-00032.bin",
+    "h.3.input_layernorm.weight": "pytorch_model_00005-of-00032.bin",
+    "h.3.mlp.dense_4h_to_h.bias": "pytorch_model_00005-of-00032.bin",
+    "h.3.mlp.dense_4h_to_h.weight": "pytorch_model_00005-of-00032.bin",
+    "h.3.mlp.dense_h_to_4h.bias": "pytorch_model_00005-of-00032.bin",
+    "h.3.mlp.dense_h_to_4h.weight": "pytorch_model_00005-of-00032.bin",
+    "h.3.post_attention_layernorm.bias": "pytorch_model_00005-of-00032.bin",
+    "h.3.post_attention_layernorm.weight": "pytorch_model_00005-of-00032.bin",
+    "h.3.self_attention.dense.bias": "pytorch_model_00005-of-00032.bin",
+    "h.3.self_attention.dense.weight": "pytorch_model_00005-of-00032.bin",
+    "h.3.self_attention.query_key_value.bias": "pytorch_model_00005-of-00032.bin",
+    "h.3.self_attention.query_key_value.weight": "pytorch_model_00005-of-00032.bin",
+    "h.4.input_layernorm.bias": "pytorch_model_00006-of-00032.bin",
+    "h.4.input_layernorm.weight": "pytorch_model_00006-of-00032.bin",
+    "h.4.mlp.dense_4h_to_h.bias": "pytorch_model_00006-of-00032.bin",
+    "h.4.mlp.dense_4h_to_h.weight": "pytorch_model_00006-of-00032.bin",
+    "h.4.mlp.dense_h_to_4h.bias": "pytorch_model_00006-of-00032.bin",
+    "h.4.mlp.dense_h_to_4h.weight": "pytorch_model_00006-of-00032.bin",
+    "h.4.post_attention_layernorm.bias": "pytorch_model_00006-of-00032.bin",
+    "h.4.post_attention_layernorm.weight": "pytorch_model_00006-of-00032.bin",
+    "h.4.self_attention.dense.bias": "pytorch_model_00006-of-00032.bin",
+    "h.4.self_attention.dense.weight": "pytorch_model_00006-of-00032.bin",
+    "h.4.self_attention.query_key_value.bias": "pytorch_model_00006-of-00032.bin",
+    "h.4.self_attention.query_key_value.weight": "pytorch_model_00006-of-00032.bin",
+    "h.5.input_layernorm.bias": "pytorch_model_00007-of-00032.bin",
+    "h.5.input_layernorm.weight": "pytorch_model_00007-of-00032.bin",
+    "h.5.mlp.dense_4h_to_h.bias": "pytorch_model_00007-of-00032.bin",
+    "h.5.mlp.dense_4h_to_h.weight": "pytorch_model_00007-of-00032.bin",
+    "h.5.mlp.dense_h_to_4h.bias": "pytorch_model_00007-of-00032.bin",
+    "h.5.mlp.dense_h_to_4h.weight": "pytorch_model_00007-of-00032.bin",
+    "h.5.post_attention_layernorm.bias": "pytorch_model_00007-of-00032.bin",
+    "h.5.post_attention_layernorm.weight": "pytorch_model_00007-of-00032.bin",
+    "h.5.self_attention.dense.bias": "pytorch_model_00007-of-00032.bin",
+    "h.5.self_attention.dense.weight": "pytorch_model_00007-of-00032.bin",
+    "h.5.self_attention.query_key_value.bias": "pytorch_model_00007-of-00032.bin",
+    "h.5.self_attention.query_key_value.weight": "pytorch_model_00007-of-00032.bin",
+    "h.6.input_layernorm.bias": "pytorch_model_00008-of-00032.bin",
+    "h.6.input_layernorm.weight": "pytorch_model_00008-of-00032.bin",
+    "h.6.mlp.dense_4h_to_h.bias": "pytorch_model_00008-of-00032.bin",
+    "h.6.mlp.dense_4h_to_h.weight": "pytorch_model_00008-of-00032.bin",
+    "h.6.mlp.dense_h_to_4h.bias": "pytorch_model_00008-of-00032.bin",
+    "h.6.mlp.dense_h_to_4h.weight": "pytorch_model_00008-of-00032.bin",
+    "h.6.post_attention_layernorm.bias": "pytorch_model_00008-of-00032.bin",
+    "h.6.post_attention_layernorm.weight": "pytorch_model_00008-of-00032.bin",
+    "h.6.self_attention.dense.bias": "pytorch_model_00008-of-00032.bin",
+    "h.6.self_attention.dense.weight": "pytorch_model_00008-of-00032.bin",
+    "h.6.self_attention.query_key_value.bias": "pytorch_model_00008-of-00032.bin",
+    "h.6.self_attention.query_key_value.weight": "pytorch_model_00008-of-00032.bin",
+    "h.7.input_layernorm.bias": "pytorch_model_00009-of-00032.bin",
+    "h.7.input_layernorm.weight": "pytorch_model_00009-of-00032.bin",
+    "h.7.mlp.dense_4h_to_h.bias": "pytorch_model_00009-of-00032.bin",
+    "h.7.mlp.dense_4h_to_h.weight": "pytorch_model_00009-of-00032.bin",
+    "h.7.mlp.dense_h_to_4h.bias": "pytorch_model_00009-of-00032.bin",
+    "h.7.mlp.dense_h_to_4h.weight": "pytorch_model_00009-of-00032.bin",
+    "h.7.post_attention_layernorm.bias": "pytorch_model_00009-of-00032.bin",
+    "h.7.post_attention_layernorm.weight": "pytorch_model_00009-of-00032.bin",
+    "h.7.self_attention.dense.bias": "pytorch_model_00009-of-00032.bin",
+    "h.7.self_attention.dense.weight": "pytorch_model_00009-of-00032.bin",
+    "h.7.self_attention.query_key_value.bias": "pytorch_model_00009-of-00032.bin",
+    "h.7.self_attention.query_key_value.weight": "pytorch_model_00009-of-00032.bin",
+    "h.8.input_layernorm.bias": "pytorch_model_00010-of-00032.bin",
+    "h.8.input_layernorm.weight": "pytorch_model_00010-of-00032.bin",
+    "h.8.mlp.dense_4h_to_h.bias": "pytorch_model_00010-of-00032.bin",
+    "h.8.mlp.dense_4h_to_h.weight": "pytorch_model_00010-of-00032.bin",
+    "h.8.mlp.dense_h_to_4h.bias": "pytorch_model_00010-of-00032.bin",
+    "h.8.mlp.dense_h_to_4h.weight": "pytorch_model_00010-of-00032.bin",
+    "h.8.post_attention_layernorm.bias": "pytorch_model_00010-of-00032.bin",
+    "h.8.post_attention_layernorm.weight": "pytorch_model_00010-of-00032.bin",
+    "h.8.self_attention.dense.bias": "pytorch_model_00010-of-00032.bin",
+    "h.8.self_attention.dense.weight": "pytorch_model_00010-of-00032.bin",
+    "h.8.self_attention.query_key_value.bias": "pytorch_model_00010-of-00032.bin",
+    "h.8.self_attention.query_key_value.weight": "pytorch_model_00010-of-00032.bin",
+    "h.9.input_layernorm.bias": "pytorch_model_00011-of-00032.bin",
+    "h.9.input_layernorm.weight": "pytorch_model_00011-of-00032.bin",
+    "h.9.mlp.dense_4h_to_h.bias": "pytorch_model_00011-of-00032.bin",
+    "h.9.mlp.dense_4h_to_h.weight": "pytorch_model_00011-of-00032.bin",
+    "h.9.mlp.dense_h_to_4h.bias": "pytorch_model_00011-of-00032.bin",
+    "h.9.mlp.dense_h_to_4h.weight": "pytorch_model_00011-of-00032.bin",
+    "h.9.post_attention_layernorm.bias": "pytorch_model_00011-of-00032.bin",
+    "h.9.post_attention_layernorm.weight": "pytorch_model_00011-of-00032.bin",
+    "h.9.self_attention.dense.bias": "pytorch_model_00011-of-00032.bin",
+    "h.9.self_attention.dense.weight": "pytorch_model_00011-of-00032.bin",
+    "h.9.self_attention.query_key_value.bias": "pytorch_model_00011-of-00032.bin",
+    "h.9.self_attention.query_key_value.weight": "pytorch_model_00011-of-00032.bin",
+    "ln_f.bias": "pytorch_model_00032-of-00032.bin",
+    "ln_f.weight": "pytorch_model_00032-of-00032.bin",
+    "word_embeddings.weight": "pytorch_model_00001-of-00032.bin",
+    "word_embeddings_layernorm.bias": "pytorch_model_00001-of-00032.bin",
+    "word_embeddings_layernorm.weight": "pytorch_model_00001-of-00032.bin"
+  }
+}

pytorch_model_00001-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b86ad2b57aeba3b565619a948faa1929c405711b9edb74dc5b43bfa021ceeb9
+size 2055226892

pytorch_model_00002-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1f404e839ddf48a8cf5af28e5ebab94eafa0c6acd6957870f5bf7f2f28a10f1
+size 402763943

pytorch_model_00003-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47847f23db64b20428b5df214a44ac3ee811a884c4727eabcf345ca1f86c1c73
+size 402763943

pytorch_model_00004-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a22faa48c32c58f40b04f7b4d9a44f8bdd00e21d3c1ffd68a3ab84ec81b7c152
+size 402763943

pytorch_model_00005-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d023d5164d172cdfd103a733230ebbfcb36ae03d2b3a4f61a962ad24010cb2d
+size 402763943

pytorch_model_00006-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52c12a9224c79af55e4c77d90a008fd96b79858ce12634b9de2601deb2d838df
+size 402763943

pytorch_model_00007-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93d20aa34cf6b3ca9527d5f673bd876f092511643b48c584f20c2fe961763c06
+size 402763943

pytorch_model_00008-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30cf787bb852f7d9463f47ee201fc3ac7bdb5e030f6bb456a93fd198d5de1957
+size 402763943

pytorch_model_00009-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6ac3105c1fbceed77e4c1605ac570645f7c49cd72be043a4ac4620f10fd21ab
+size 402763943

pytorch_model_00010-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a54edb90b47fa8ae6f2877e6e2bf8ff1b2cbb88c3a9512e3c5b12d842339929
+size 402763943

pytorch_model_00011-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd6f1b818e38928672068d3eae02ff376db00eebe72f3342d54d8c9cf0d9a508
+size 402763943

pytorch_model_00012-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14385421abf3e0e5c977c7c5ace936df7417e88477bb365f413afdb47dcb13d2
+size 402763943

pytorch_model_00013-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1975f2b734ab2d696b10dc9ffa60dfe5351f3c8c2c0e84bf7eec4362b8a8d43d
+size 402763943

pytorch_model_00014-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:944a67601b5b2e7992bf5eaba0e070171ab12c9654fb83c3519d4449d5b162b7
+size 402763943

pytorch_model_00015-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08b1baaedbeb1bad55e17e525347f2c1ee4dc3607387eb489db9430cc0db34fb
+size 402763943

pytorch_model_00016-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62f3edab7079ccab52a3a95839e6f257b338e83e21a9a28e8f5d6ab2329dfae3
+size 402763943

pytorch_model_00017-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a9bee789c58e77235f1aa7c84524234fc44b61f6836a5252829ed3d33678a81
+size 402763943

pytorch_model_00018-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b29ac601330398786de8905b65d40577e2d51baae1167baddbcd9cbdd9766099
+size 402763943

pytorch_model_00019-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3f78b96c3ba9f57e9afb795b21b8e6bc7660db41eb82788280431f994d5799c
+size 402763943

pytorch_model_00020-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ecd44e311822100b789b004d53e60451d579232e65dcb8d777bafc3bb494e3f
+size 402763943

pytorch_model_00021-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f12433f71622755d39414bb502c89d4abc1beba4fe0349952e5b0e8d37db4cd9
+size 402763943

pytorch_model_00022-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ca9a65b39930ed4ecdbc54369f04b01ed1c71acdc23e20081ab78a4cc28f45b
+size 402763943

pytorch_model_00023-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f8487c084fcd99d69b5bd68f634063869313bd6075f63498596560a02f1adf1
+size 402763943

pytorch_model_00024-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f060e11320cd910da6df619ea731be66a4754b958ca64b332be858342a02b4f
+size 402763943

pytorch_model_00025-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b82a3046961d5a7ce7754ebcfbe4a27eaa6b7a1985e2e11ef947b847c4259387
+size 402763943

pytorch_model_00026-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4555360f78ac8e3d8c2a1a9c171ec050f2ced6125154e1cd326393a81897d2a
+size 402763943

pytorch_model_00027-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27e24b426c31b3eaa69d8a7b82ef2267c13145fbfd009b777909a03db279b77b
+size 402763943

pytorch_model_00028-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67c4f4af375c9b45b315a7f5fa5ab78c20d41fc9f721c7a254c144f1828feebc
+size 402763943

pytorch_model_00029-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a759fe8be20c4333b73024b8c99e3afdc216611bb5002ec13222cc7ea299e044
+size 402763943

pytorch_model_00030-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b23edddf82f23853d6dc0ac487387282e809ff56eeb5f15e437946988436ba15
+size 402763943

pytorch_model_00031-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b311c2f6c2cbe7e4ff9cf94aa0dd4c244dce3be8fcd707a143cf72788511a589
+size 402763943

pytorch_model_00032-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1952cf434827b8a25b0ce30b17d0f762d18beb3f0abb9e7241d324076d53e69e
+size 17595

special_tokens_map.json

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

tensorboard/events.out.tfevents.1670162155.nid007107.106779.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:152e0630975b027ed37d48d5a39cd9cae29ed441fa9cf6c2204425151a59225e
+size 2400100

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"}