upload

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "coincheung/bloomz-7b1-mt-nvl-cllv",
+  "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,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.29.2",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 50048
+}

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": "4.29.2"
+}

pytorch_model-00001-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f66f3bceb593ef136902422762d0a69051d4b4c3bbaba3ecf0c25f1277c6a11e
+size 947060397

pytorch_model-00002-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d3458f6b0b3bc91dc13596e2139510638de9ff27130fdc6a222bdffb565acd7
+size 939778659

pytorch_model-00003-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:685dea39712674149b0a9734cac4cce89c3c9ecede5081d67a3b7bdccd2c3078
+size 939771079

pytorch_model-00004-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:725d80e6e36fc09a8154ee61b02f5a73c5f9b7de19fda3ff7f055822b1e75c20
+size 939796331

pytorch_model-00005-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4134965accd5a0aad4e0037aa90d93410a93830cf129ad6c0be43686f8f2893
+size 939778659

pytorch_model-00006-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e860b9717399b8e8bc68de2057b1c751d100797358af9f0a5500d175e4a9418
+size 939771079

pytorch_model-00007-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92e86714ecfb9071c9e1038b8e9b73ae5110d94d1aeb748bf1bdfcaa4f802b04
+size 939796331

pytorch_model-00008-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6ef477bd583f8d44279742448eceac2e016d07ebe8ab1d236edbcc5778db4c5
+size 939778659

pytorch_model-00009-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8d00a0f5037e3446f82220d4fa17b01b40a418a25a8db3c4b1375e6decbe9df
+size 939771079

pytorch_model-00010-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:002700fb45500b50da38032ca9c1179855a4f5c387392cceafe3e060e187569e
+size 939796331

pytorch_model-00011-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18f3147f06fe1424caf7aedcbf75a0f52ecd9984c4e6aede278c9e7489716d4
+size 939778659

pytorch_model-00012-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97a6b4ce5b9f6cbf0f7f574c8cd80c8c1548e70a59efcd36458c5b7ee9f4f1ca
+size 939771079

pytorch_model-00013-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec54a0c8b3526076c446bf7e25c0db41bfbe1e15e644b5e12ff31eeebeb14a43
+size 939796331

pytorch_model-00014-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6247f80a60d18937ba3be7b6dcd5e74b80ced7849e85358cdd82d2fea2f22fe0
+size 678488784

pytorch_model.bin.index.json

@@ -0,0 +1,373 @@
+{
+  "metadata": {
+    "total_size": 12902809600
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00014-of-00014.bin",
+    "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00014.bin",
+    "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00014.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00014.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00014.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00014.bin",
+    "transformer.h.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00014.bin",
+    "transformer.h.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
+    "transformer.h.0.self_attention.dense.bias": "pytorch_model-00001-of-00014.bin",
+    "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00014.bin",
+    "transformer.h.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00014.bin",
+    "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00014.bin",
+    "transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00014.bin",
+    "transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00014.bin",
+    "transformer.h.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
+    "transformer.h.1.self_attention.dense.bias": "pytorch_model-00001-of-00014.bin",
+    "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00014.bin",
+    "transformer.h.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00014.bin",
+    "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00014.bin",
+    "transformer.h.10.input_layernorm.bias": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.10.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.10.post_attention_layernorm.bias": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.10.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.10.self_attention.dense.bias": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.10.self_attention.dense.weight": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.10.self_attention.query_key_value.bias": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.11.input_layernorm.bias": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.11.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.11.post_attention_layernorm.bias": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.11.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.11.self_attention.dense.bias": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.11.self_attention.dense.weight": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.11.self_attention.query_key_value.bias": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.12.input_layernorm.bias": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.12.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.12.post_attention_layernorm.bias": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.12.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.12.self_attention.dense.bias": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.12.self_attention.dense.weight": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.12.self_attention.query_key_value.bias": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.13.input_layernorm.bias": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.13.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.13.post_attention_layernorm.bias": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.13.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.13.self_attention.dense.bias": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.13.self_attention.dense.weight": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.13.self_attention.query_key_value.bias": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.14.input_layernorm.bias": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.14.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.14.post_attention_layernorm.bias": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.14.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.14.self_attention.dense.bias": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.14.self_attention.dense.weight": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.14.self_attention.query_key_value.bias": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.15.input_layernorm.bias": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.15.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.15.post_attention_layernorm.bias": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.15.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.15.self_attention.dense.bias": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.15.self_attention.dense.weight": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.15.self_attention.query_key_value.bias": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00007-of-00014.bin",
+    "transformer.h.16.input_layernorm.bias": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.16.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.16.post_attention_layernorm.bias": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.16.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.16.self_attention.dense.bias": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.16.self_attention.dense.weight": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.16.self_attention.query_key_value.bias": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.17.input_layernorm.bias": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.17.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.17.post_attention_layernorm.bias": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.17.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.17.self_attention.dense.bias": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.17.self_attention.dense.weight": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.17.self_attention.query_key_value.bias": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00008-of-00014.bin",
+    "transformer.h.18.input_layernorm.bias": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.18.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.18.post_attention_layernorm.bias": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.18.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.18.self_attention.dense.bias": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.18.self_attention.dense.weight": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.18.self_attention.query_key_value.bias": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.19.input_layernorm.bias": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.19.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.19.post_attention_layernorm.bias": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.19.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.19.self_attention.dense.bias": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.19.self_attention.dense.weight": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.19.self_attention.query_key_value.bias": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.2.input_layernorm.bias": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.2.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.2.post_attention_layernorm.bias": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.2.self_attention.dense.bias": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.2.self_attention.dense.weight": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.2.self_attention.query_key_value.bias": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.20.input_layernorm.bias": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.20.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.bias": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.bias": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.20.post_attention_layernorm.bias": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.20.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.20.self_attention.dense.bias": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.20.self_attention.dense.weight": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.20.self_attention.query_key_value.bias": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.21.input_layernorm.bias": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.21.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.bias": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.bias": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.21.post_attention_layernorm.bias": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.21.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.21.self_attention.dense.bias": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.21.self_attention.dense.weight": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.21.self_attention.query_key_value.bias": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.22.input_layernorm.bias": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.22.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.bias": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.bias": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.22.post_attention_layernorm.bias": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.22.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.22.self_attention.dense.bias": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.22.self_attention.dense.weight": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.22.self_attention.query_key_value.bias": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00010-of-00014.bin",
+    "transformer.h.23.input_layernorm.bias": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.23.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.bias": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.bias": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.23.post_attention_layernorm.bias": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.23.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.23.self_attention.dense.bias": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.23.self_attention.dense.weight": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.23.self_attention.query_key_value.bias": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.24.input_layernorm.bias": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.24.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.bias": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.bias": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.24.post_attention_layernorm.bias": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.24.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.24.self_attention.dense.bias": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.24.self_attention.dense.weight": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.24.self_attention.query_key_value.bias": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00011-of-00014.bin",
+    "transformer.h.25.input_layernorm.bias": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.25.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.bias": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.bias": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.25.post_attention_layernorm.bias": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.25.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.25.self_attention.dense.bias": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.25.self_attention.dense.weight": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.25.self_attention.query_key_value.bias": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.26.input_layernorm.bias": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.26.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.bias": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.bias": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.26.post_attention_layernorm.bias": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.26.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.26.self_attention.dense.bias": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.26.self_attention.dense.weight": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.26.self_attention.query_key_value.bias": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.27.input_layernorm.bias": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.27.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.bias": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.bias": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.27.post_attention_layernorm.bias": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.27.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.27.self_attention.dense.bias": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.27.self_attention.dense.weight": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.27.self_attention.query_key_value.bias": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.28.input_layernorm.bias": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.28.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.bias": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.bias": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.28.post_attention_layernorm.bias": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.28.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.28.self_attention.dense.bias": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.28.self_attention.dense.weight": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.28.self_attention.query_key_value.bias": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.29.input_layernorm.bias": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.29.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.bias": "pytorch_model-00014-of-00014.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00014.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.bias": "pytorch_model-00014-of-00014.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00014.bin",
+    "transformer.h.29.post_attention_layernorm.bias": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.29.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.29.self_attention.dense.bias": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.29.self_attention.dense.weight": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.29.self_attention.query_key_value.bias": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00013-of-00014.bin",
+    "transformer.h.3.input_layernorm.bias": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.3.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.3.post_attention_layernorm.bias": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.3.self_attention.dense.bias": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.3.self_attention.dense.weight": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.3.self_attention.query_key_value.bias": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00002-of-00014.bin",
+    "transformer.h.4.input_layernorm.bias": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.4.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.4.post_attention_layernorm.bias": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.4.self_attention.dense.bias": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.4.self_attention.dense.weight": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.4.self_attention.query_key_value.bias": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.5.input_layernorm.bias": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.5.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.5.post_attention_layernorm.bias": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.5.self_attention.dense.bias": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.5.self_attention.dense.weight": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.5.self_attention.query_key_value.bias": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.6.input_layernorm.bias": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.6.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.6.post_attention_layernorm.bias": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.6.self_attention.dense.bias": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.6.self_attention.dense.weight": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.6.self_attention.query_key_value.bias": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.7.input_layernorm.bias": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.7.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.7.post_attention_layernorm.bias": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.7.self_attention.dense.bias": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.7.self_attention.dense.weight": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.7.self_attention.query_key_value.bias": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.8.input_layernorm.bias": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.8.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.8.post_attention_layernorm.bias": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.8.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.8.self_attention.dense.bias": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.8.self_attention.dense.weight": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.8.self_attention.query_key_value.bias": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00004-of-00014.bin",
+    "transformer.h.9.input_layernorm.bias": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.9.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.9.post_attention_layernorm.bias": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.9.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.9.self_attention.dense.bias": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.9.self_attention.dense.weight": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.9.self_attention.query_key_value.bias": "pytorch_model-00005-of-00014.bin",
+    "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00005-of-00014.bin",
+    "transformer.ln_f.bias": "pytorch_model-00014-of-00014.bin",
+    "transformer.ln_f.weight": "pytorch_model-00014-of-00014.bin",
+    "transformer.word_embeddings.weight": "pytorch_model-00001-of-00014.bin",
+    "transformer.word_embeddings_layernorm.bias": "pytorch_model-00001-of-00014.bin",
+    "transformer.word_embeddings_layernorm.weight": "pytorch_model-00001-of-00014.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2676d4ca29ca1750f6ff203328d73b189321dc5776ceede037cbd36541d70c0
+size 757958

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}