Upload folder using huggingface_hub

adapter/.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

adapter/adapter_config.json

@@ -0,0 +1,20 @@
+{
+  "base_model_name_or_path": "tiiuae/falcon-40b",
+  "bias": "none",
+  "enable_lora": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "merge_weights": false,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "target_modules": [
+    "dense_4h_to_h",
+    "dense",
+    "query_key_value",
+    "dense_h_to_4h"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40ff3d1406b23ca62efc65e16989d7eae5a80362394276a4232924cd2d218847
+size 1777506445

adapter/extra_embeddings.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab19e36e25a6a993ac09d53ae99ba7dc25eb671bf4003e7de0a9bc2d321c023f
+size 262918

adapter/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "additional_special_tokens": [
+    "<|prefix_end|>",
+    ">>PREFIX<<",
+    ">>QUESTION<<",
+    "<|prompter|>",
+    ">>MIDDLE<<",
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>DOMAIN<<",
+    "<|prefix_begin|>",
+    ">>ANSWER<<",
+    "<|system|>",
+    ">>COMMENT<<",
+    ">>SUMMARY<<",
+    ">>SUFFIX<<",
+    "<|assistant|>",
+    ">>INTRODUCTION<<"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "sep_token": "<|endoftext|>"
+}

adapter/tokenizer_config.json

@@ -0,0 +1,8 @@
+{
+  "add_prefix_space": false,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "tiiuae/falcon-40b",
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "RWForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "tiiuae/falcon-40b--configuration_RW.RWConfig",
+    "AutoModel": "tiiuae/falcon-40b--modelling_RW.RWModel",
+    "AutoModelForCausalLM": "tiiuae/falcon-40b--modelling_RW.RWForCausalLM",
+    "AutoModelForQuestionAnswering": "tiiuae/falcon-40b--modelling_RW.RWForQuestionAnswering",
+    "AutoModelForSequenceClassification": "tiiuae/falcon-40b--modelling_RW.RWForSequenceClassification",
+    "AutoModelForTokenClassification": "tiiuae/falcon-40b--modelling_RW.RWForTokenClassification"
+  },
+  "bias": false,
+  "bos_token_id": null,
+  "eos_token_id": 11,
+  "hidden_dropout": 0.0,
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "RefinedWeb",
+  "n_head": 128,
+  "n_head_kv": 8,
+  "n_layer": 60,
+  "pad_token_id": 11,
+  "parallel_attn": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 65040
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.30.2"
+}

pytorch_model-00001-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4fdb08281cdec48929f290635988636e6ab5b7a90f4df9193e6c8bdb9fee406
+size 9505032413

pytorch_model-00002-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:932471367f855abb116eec38d5524272b1e341420023526971b06aa073945b8d
+size 9513159151

pytorch_model-00003-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f266b956ff7629ac2e973091c8170572e106390172ad1c8fd26c5faa5ad0c454
+size 9513159151

pytorch_model-00004-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d78f737f213f6681d776734aa327ac36fee7bca3538d8ccd51adefad8bf3d898
+size 9513159151

pytorch_model-00005-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d095111033c747cb1907c14166f4d97485c70bbb2eac8661ea3208807ed66d6f
+size 9513159151

pytorch_model-00006-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bcdecca78655dcf8bb676e65c368e66e069d3c95d9216ac58afbb9a0dcd66d6
+size 9513159151

pytorch_model-00007-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6d3c16997727da63cb1d215db9076039de66cb8bcfb7c5322fa541eedfcc013
+size 9513159151

pytorch_model-00008-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56e2f260aec950b2394cbff8f93b8ceaf10ac71f9ceaccc854f68ea4f2715f94
+size 9513159151

pytorch_model-00009-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0b4055650f40ca29e4714f25a240c46a2d3f0808a3816e1e320b92dd53a128c
+size 6509866711

pytorch_model.bin.index.json

@@ -0,0 +1,491 @@
+{
+  "metadata": {
+    "total_size": 82606850048
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.0.ln_attn.bias": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.0.ln_attn.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.0.ln_mlp.bias": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.0.ln_mlp.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.1.ln_attn.bias": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.1.ln_attn.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.1.ln_mlp.bias": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.1.ln_mlp.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.10.ln_attn.bias": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.10.ln_attn.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.10.ln_mlp.bias": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.10.ln_mlp.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.10.self_attention.dense.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.11.ln_attn.bias": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.11.ln_attn.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.11.ln_mlp.bias": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.11.ln_mlp.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.11.self_attention.dense.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.12.ln_attn.bias": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.12.ln_attn.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.12.ln_mlp.bias": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.12.ln_mlp.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.12.self_attention.dense.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.13.ln_attn.bias": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.13.ln_attn.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.13.ln_mlp.bias": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.13.ln_mlp.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.13.self_attention.dense.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.14.ln_attn.bias": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.14.ln_attn.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.14.ln_mlp.bias": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.14.ln_mlp.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.14.self_attention.dense.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.15.ln_attn.bias": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.15.ln_attn.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.15.ln_mlp.bias": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.15.ln_mlp.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.15.self_attention.dense.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.16.ln_attn.bias": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.16.ln_attn.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.16.ln_mlp.bias": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.16.ln_mlp.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.16.self_attention.dense.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.17.ln_attn.bias": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.17.ln_attn.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.17.ln_mlp.bias": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.17.ln_mlp.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.17.self_attention.dense.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.18.ln_attn.bias": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.18.ln_attn.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.18.ln_mlp.bias": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.18.ln_mlp.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.18.self_attention.dense.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.19.ln_attn.bias": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.19.ln_attn.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.19.ln_mlp.bias": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.19.ln_mlp.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.19.self_attention.dense.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.2.ln_attn.bias": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.2.ln_attn.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.2.ln_mlp.bias": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.2.ln_mlp.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.20.ln_attn.bias": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.20.ln_attn.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.20.ln_mlp.bias": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.20.ln_mlp.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.20.self_attention.dense.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
+    "transformer.h.21.ln_attn.bias": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.21.ln_attn.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.21.ln_mlp.bias": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.21.ln_mlp.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.21.self_attention.dense.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.22.ln_attn.bias": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.22.ln_attn.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.22.ln_mlp.bias": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.22.ln_mlp.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.22.self_attention.dense.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.23.ln_attn.bias": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.23.ln_attn.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.23.ln_mlp.bias": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.23.ln_mlp.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.23.self_attention.dense.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.24.ln_attn.bias": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.24.ln_attn.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.24.ln_mlp.bias": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.24.ln_mlp.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.24.self_attention.dense.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.25.ln_attn.bias": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.25.ln_attn.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.25.ln_mlp.bias": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.25.ln_mlp.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.25.self_attention.dense.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.26.ln_attn.bias": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.26.ln_attn.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.26.ln_mlp.bias": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.26.ln_mlp.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.26.self_attention.dense.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.27.ln_attn.bias": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.27.ln_attn.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.27.ln_mlp.bias": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.27.ln_mlp.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.27.self_attention.dense.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
+    "transformer.h.28.ln_attn.bias": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.28.ln_attn.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.28.ln_mlp.bias": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.28.ln_mlp.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.28.self_attention.dense.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.29.ln_attn.bias": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.29.ln_attn.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.29.ln_mlp.bias": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.29.ln_mlp.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.29.self_attention.dense.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.3.ln_attn.bias": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.3.ln_attn.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.3.ln_mlp.bias": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.3.ln_mlp.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.30.ln_attn.bias": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.30.ln_attn.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.30.ln_mlp.bias": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.30.ln_mlp.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.30.self_attention.dense.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.31.ln_attn.bias": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.31.ln_attn.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.31.ln_mlp.bias": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.31.ln_mlp.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.31.self_attention.dense.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.32.ln_attn.bias": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.32.ln_attn.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.32.ln_mlp.bias": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.32.ln_mlp.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.32.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.32.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.32.self_attention.dense.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.32.self_attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.33.ln_attn.bias": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.33.ln_attn.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.33.ln_mlp.bias": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.33.ln_mlp.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.33.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.33.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.33.self_attention.dense.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.33.self_attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.34.ln_attn.bias": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.34.ln_attn.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.34.ln_mlp.bias": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.34.ln_mlp.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.34.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.34.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.34.self_attention.dense.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.34.self_attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
+    "transformer.h.35.ln_attn.bias": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.35.ln_attn.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.35.ln_mlp.bias": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.35.ln_mlp.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.35.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.35.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.35.self_attention.dense.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.35.self_attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.36.ln_attn.bias": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.36.ln_attn.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.36.ln_mlp.bias": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.36.ln_mlp.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.36.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.36.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.36.self_attention.dense.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.36.self_attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.37.ln_attn.bias": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.37.ln_attn.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.37.ln_mlp.bias": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.37.ln_mlp.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.37.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.37.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.37.self_attention.dense.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.37.self_attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.38.ln_attn.bias": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.38.ln_attn.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.38.ln_mlp.bias": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.38.ln_mlp.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.38.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.38.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.38.self_attention.dense.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.38.self_attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.39.ln_attn.bias": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.39.ln_attn.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.39.ln_mlp.bias": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.39.ln_mlp.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.39.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.39.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.39.self_attention.dense.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.39.self_attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.4.ln_attn.bias": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.4.ln_attn.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.4.ln_mlp.bias": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.4.ln_mlp.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.4.self_attention.dense.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.40.ln_attn.bias": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.40.ln_attn.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.40.ln_mlp.bias": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.40.ln_mlp.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.40.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.40.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.40.self_attention.dense.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.40.self_attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.41.ln_attn.bias": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.41.ln_attn.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.41.ln_mlp.bias": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.41.ln_mlp.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.41.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.41.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.41.self_attention.dense.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.41.self_attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
+    "transformer.h.42.ln_attn.bias": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.42.ln_attn.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.42.ln_mlp.bias": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.42.ln_mlp.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.42.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.42.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.42.self_attention.dense.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.42.self_attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.43.ln_attn.bias": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.43.ln_attn.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.43.ln_mlp.bias": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.43.ln_mlp.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.43.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.43.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.43.self_attention.dense.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.43.self_attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.44.ln_attn.bias": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.44.ln_attn.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.44.ln_mlp.bias": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.44.ln_mlp.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.44.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.44.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.44.self_attention.dense.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.44.self_attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.45.ln_attn.bias": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.45.ln_attn.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.45.ln_mlp.bias": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.45.ln_mlp.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.45.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.45.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.45.self_attention.dense.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.45.self_attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.46.ln_attn.bias": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.46.ln_attn.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.46.ln_mlp.bias": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.46.ln_mlp.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.46.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.46.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.46.self_attention.dense.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.46.self_attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.47.ln_attn.bias": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.47.ln_attn.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.47.ln_mlp.bias": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.47.ln_mlp.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.47.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.47.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.47.self_attention.dense.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.47.self_attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.48.ln_attn.bias": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.48.ln_attn.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.48.ln_mlp.bias": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.48.ln_mlp.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.48.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.48.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.48.self_attention.dense.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.48.self_attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
+    "transformer.h.49.ln_attn.bias": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.49.ln_attn.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.49.ln_mlp.bias": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.49.ln_mlp.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.49.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.49.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.49.self_attention.dense.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.49.self_attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.5.ln_attn.bias": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.5.ln_attn.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.5.ln_mlp.bias": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.5.ln_mlp.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.5.self_attention.dense.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.50.ln_attn.bias": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.50.ln_attn.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.50.ln_mlp.bias": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.50.ln_mlp.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.50.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.50.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.50.self_attention.dense.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.50.self_attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.51.ln_attn.bias": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.51.ln_attn.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.51.ln_mlp.bias": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.51.ln_mlp.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.51.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.51.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.51.self_attention.dense.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.51.self_attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.52.ln_attn.bias": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.52.ln_attn.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.52.ln_mlp.bias": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.52.ln_mlp.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.52.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.52.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.52.self_attention.dense.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.52.self_attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.53.ln_attn.bias": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.53.ln_attn.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.53.ln_mlp.bias": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.53.ln_mlp.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.53.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.53.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.53.self_attention.dense.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.53.self_attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.54.ln_attn.bias": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.54.ln_attn.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.54.ln_mlp.bias": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.54.ln_mlp.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.54.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.54.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.54.self_attention.dense.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.54.self_attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.55.ln_attn.bias": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.55.ln_attn.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.55.ln_mlp.bias": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.55.ln_mlp.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.55.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.55.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.55.self_attention.dense.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.55.self_attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
+    "transformer.h.56.ln_attn.bias": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.56.ln_attn.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.56.ln_mlp.bias": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.56.ln_mlp.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.56.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.56.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.56.self_attention.dense.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.56.self_attention.query_key_value.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.57.ln_attn.bias": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.57.ln_attn.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.57.ln_mlp.bias": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.57.ln_mlp.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.57.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.57.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.57.self_attention.dense.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.57.self_attention.query_key_value.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.58.ln_attn.bias": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.58.ln_attn.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.58.ln_mlp.bias": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.58.ln_mlp.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.58.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.58.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.58.self_attention.dense.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.58.self_attention.query_key_value.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.59.ln_attn.bias": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.59.ln_attn.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.59.ln_mlp.bias": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.59.ln_mlp.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.59.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.59.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.59.self_attention.dense.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.59.self_attention.query_key_value.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.h.6.ln_attn.bias": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.6.ln_attn.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.6.ln_mlp.bias": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.6.ln_mlp.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.6.self_attention.dense.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
+    "transformer.h.7.ln_attn.bias": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.7.ln_attn.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.7.ln_mlp.bias": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.7.ln_mlp.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.7.self_attention.dense.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.8.ln_attn.bias": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.8.ln_attn.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.8.ln_mlp.bias": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.8.ln_mlp.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.8.self_attention.dense.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.9.ln_attn.bias": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.9.ln_attn.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.9.ln_mlp.bias": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.9.ln_mlp.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.9.self_attention.dense.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
+    "transformer.ln_f.bias": "pytorch_model-00009-of-00009.bin",
+    "transformer.ln_f.weight": "pytorch_model-00009-of-00009.bin",
+    "transformer.word_embeddings.weight": "pytorch_model-00001-of-00009.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "additional_special_tokens": [
+    "<|prefix_end|>",
+    ">>PREFIX<<",
+    ">>QUESTION<<",
+    "<|prompter|>",
+    ">>MIDDLE<<",
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>DOMAIN<<",
+    "<|prefix_begin|>",
+    ">>ANSWER<<",
+    "<|system|>",
+    ">>COMMENT<<",
+    ">>SUMMARY<<",
+    ">>SUFFIX<<",
+    "<|assistant|>",
+    ">>INTRODUCTION<<"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "sep_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,7 @@
+{
+  "add_prefix_space": false,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}