First Commit

.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

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "/gpfs/home/cs/yangyuchen/yushengliao/Medical_LLM/FastChat/checkpoints/bloomz_7b_chat_v1.3/checkpoint-9942",
+  "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": 4,
+  "seq_length": 2048,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250880
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.28.1"
+}

pytorch_model-00001-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a76dc8f5351fef1c98664c09992f4d4236c649411455c1a9046cf1aff47116c
+size 9950527709

pytorch_model-00002-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6945fc0877a028a4e17d26a6e19a59640c1371fce837e6da5f6b2ba3fe2e928
+size 9733443563

pytorch_model-00003-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:322e0a07565f794b13945251c8ea7df38e5e37799e07707efb69fc337b93850a
+size 8592224381

pytorch_model-00004-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e2056d30b82597ef71a17d9ddf64ecfc23c1c97cb472576887cb2903042eb7a
+size 4110418858

pytorch_model.bin.index.json

@@ -0,0 +1,373 @@
+{
+  "metadata": {
+    "total_size": 32386482176
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00004-of-00004.bin",
+    "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.0.self_attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.1.self_attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.10.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.10.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.10.self_attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.10.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.10.self_attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.11.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.11.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.11.self_attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.11.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.11.self_attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.12.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.12.self_attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.12.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.12.self_attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.13.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.13.self_attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.13.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.13.self_attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.14.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.14.self_attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.14.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.14.self_attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.15.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.15.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.15.self_attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.15.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.15.self_attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.16.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.16.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.16.self_attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.16.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.16.self_attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.17.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.17.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.17.self_attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.17.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.17.self_attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.18.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.18.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.18.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.18.self_attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.18.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.18.self_attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.19.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.19.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.19.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.19.self_attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.19.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.19.self_attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.2.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.2.self_attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.20.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.20.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.20.self_attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.20.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.20.self_attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.21.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.21.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.21.self_attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.21.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.21.self_attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.22.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.22.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.22.self_attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.22.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.22.self_attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.23.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.23.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.23.self_attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.23.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.23.self_attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.24.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.24.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.24.self_attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.24.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.24.self_attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.25.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.25.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.25.self_attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.25.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.25.self_attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.26.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.26.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.26.self_attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.26.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.26.self_attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.27.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.27.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.27.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.27.self_attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.27.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.27.self_attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.28.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.28.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.28.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.28.self_attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.28.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.28.self_attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.29.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.29.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.29.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.29.self_attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.29.self_attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.29.self_attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.h.3.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.3.self_attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.4.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.4.self_attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.4.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.4.self_attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.5.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.5.self_attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.5.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.5.self_attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.6.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.6.self_attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.6.self_attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.6.self_attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.7.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.7.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.7.self_attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.7.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.7.self_attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.h.8.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.8.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.8.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.8.self_attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.8.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.8.self_attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.9.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.9.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.9.self_attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.9.self_attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.9.self_attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "transformer.ln_f.bias": "pytorch_model-00003-of-00004.bin",
+    "transformer.ln_f.weight": "pytorch_model-00003-of-00004.bin",
+    "transformer.word_embeddings.weight": "pytorch_model-00001-of-00004.bin",
+    "transformer.word_embeddings_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "transformer.word_embeddings_layernorm.weight": "pytorch_model-00001-of-00004.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<unk>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
+size 14500471

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 2548,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "tokenizer_class": "BloomTokenizerFast",
+  "unk_token": "<unk>"
+}