init

config.json

@@ -0,0 +1,18 @@
+{
+  "apply_residual_connection_post_layernorm": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 64,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "bloom",
+  "n_head": 8,
+  "n_layer": 2,
+  "pretraining_tp": 1,
+  "slow_but_exact": false,
+  "transformers_version": "4.24.0.dev0",
+  "use_cache": true,
+  "vocab_size": 250880
+}

pytorch_model.bin.index.json

@@ -0,0 +1,372 @@
+{
+  "metadata": {
+    "total_size": 12494913536
+  },
+  "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:f87df470ca847afd30dbbedf51f26dc78e16b181cdf27bc5b90e9852ffbdf552
+size 412107939

pytorch_model_00002-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c87d4714a2d13ff875e09858aec6e2311ed6af8c7b88dd9e5fcdd4731ac62a97
+size 402762945

pytorch_model_00003-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32ea55e05038880ec77868765f901509b31d807818dff13c22535391aa435cf0
+size 402762945

pytorch_model_00004-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4841f44c4e306dcc63d728e1f01b688003d30930a9f5e0033b9c553715d5bad6
+size 402762945

pytorch_model_00005-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:022b4d9710a0d935e5160f80969572673dd72bc6e9704fee3746f24716ad0885
+size 402762945

pytorch_model_00006-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:136925c731167d1bcee5504a59baedb2b8c8fd35ddd6175a58ffbac4d300ec7f
+size 402762945

pytorch_model_00007-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b3996d9f17491876c6389a4a4fdd421357ea09bac32d733c77595c146d0ba5e
+size 402762945

pytorch_model_00008-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21823e5e2b4d553ae47ba2e44856d5ee080725e700638380176b7923ee9141f1
+size 402762945

pytorch_model_00009-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62d05f68092c3e1feaf61a11560e8251a6051d922e653c5a3ae6f986d229a1d3
+size 402762945

pytorch_model_00010-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc55b367f7c705bfeca567939e3891cd78fda2ba1287dc688b9cb0a2ff68c1e7
+size 402762945

pytorch_model_00011-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b931f6b34bf61cf85e2b1e816140a23a0aca7966be0e752fce7239d5bd7a5dd
+size 402762945

pytorch_model_00012-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89bb9b8c81d6b44a9c8dae1396f87ca75693ef3d76cd695e32c452cf6b644f7c
+size 402762945

pytorch_model_00013-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:074289143c81abfe9f764c390213a09be6e746f1e1d2fb7b7120e383bed34ec9
+size 402762945

pytorch_model_00014-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc6b37f1a244d4ecd71d4240d4db0cd4a7b128737dbe3a526ff58ae2770b8fdd
+size 402762945

pytorch_model_00015-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ecd83aa78126ab1fb8c40a9b9bbce7acd0550c81b4d324e1025ee30c4d69cce
+size 402762945

pytorch_model_00016-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce1885fda2328fa734d0ea62b1d726601064b5edbb3cd2b462ef6441e7089ff4
+size 402762945

pytorch_model_00017-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aed49a398729b3da23ebd5379b704876fa50bda3a030ae5b74b4729461c2f99b
+size 402762945

pytorch_model_00018-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70d501e78e2d83d4f578e1344f72cba92353e5513b3225a502d74d5290234dba
+size 402762945

pytorch_model_00019-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e8616f0a7cd61b8f39aedcafc943d609c86b9c93a7a05cb859daababb8c494d
+size 402762945

pytorch_model_00020-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7840383337a61f8c1e41c41ed151bf98fc3a83d7a31167f3993265edcb422115
+size 402762945

pytorch_model_00021-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:483117090b37d42241290d2bd8cec03c73f66c096213b379633c83c60f6711e7
+size 402762945

pytorch_model_00022-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8843fabe2718f27ed62f85d8a2086f95358141231d2b38fcda14958f13f786b4
+size 402762945

pytorch_model_00023-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c26e8cae004a660d0bbb547fa2a1be800cc1e1d62751526b99a2ca6641f0169
+size 402762945

pytorch_model_00024-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9feedc0454fdac63e3fd1ac07344d94a5c23cb1f766915f3f5e4489b241b0fa8
+size 402762945

pytorch_model_00025-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b6b80768f151a8031353485b70400a1d63cb3929e053e317bd8e81363bab65
+size 402762945

pytorch_model_00026-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a473c4b47c48dfa074f5bcf96caa5765e1fc8cded7a37579795b80547ccd588
+size 402762945

pytorch_model_00027-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8769ee0049527de780e7d61329df46fe9198e56ac83d68b04e058e2a1f44877e
+size 402762945

pytorch_model_00028-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e941cd0bc7bdaf5bbfe3ef027f4a734e9d4af5a252cc4258c1d30c7cb1558497
+size 402762945

pytorch_model_00029-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64a262fec32fe30801678b195077961206322790105ce0594d56a57fa90a2e39
+size 402762945

pytorch_model_00030-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39ddd58c9a32909b3512b9f9393377708c702a3456f9789e4c21483a7184d04f
+size 402762945

pytorch_model_00031-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8209a216e145a53d713f6e3e60b55521c6db833eb89778beae01a5b53b231b3b
+size 402762945

pytorch_model_00032-of-00032.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53428bf97cc29cf3c2ad2c759fe0afb712936f5fb41ccdb6948ff517cec0453c
+size 17319

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "name_or_path": "/data/datasets/huggingface_transformers/pytorch/bloom-1b7-twc-german",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}