Add Model

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "/data/experiment_data/junda/chatdoctor/llama-13b-32k-medqa-open-reason-hf",
+  "architectures": [
+    "LlamaIRForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "colbert_checkpoint": true,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "type": "linear"
+  },
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.33.2",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.33.2"
+}

ir/artifact.metadata

@@ -0,0 +1,58 @@
+{
+    "query_token_id": "[unused0]",
+    "doc_token_id": "[unused1]",
+    "query_token": "[Q]",
+    "doc_token": "[D]",
+    "ncells": null,
+    "centroid_score_threshold": null,
+    "ndocs": null,
+    "load_index_with_mmap": false,
+    "index_path": null,
+    "nbits": 1,
+    "kmeans_niters": 20,
+    "resume": false,
+    "similarity": "cosine",
+    "bsize": 4,
+    "accumsteps": 1,
+    "lr": 3e-6,
+    "maxsteps": 400000,
+    "save_every": null,
+    "warmup": 20000,
+    "warmup_bert": null,
+    "relu": false,
+    "nway": 64,
+    "use_ib_negatives": false,
+    "reranker": false,
+    "distillation_alpha": 1.0,
+    "ignore_scores": false,
+    "model_name": null,
+    "query_maxlen": 512,
+    "attend_to_mask_tokens": false,
+    "interaction": "colbert",
+    "dim": 128,
+    "doc_maxlen": 128,
+    "mask_punctuation": true,
+    "checkpoint": "\/data\/experiment_data\/junda\/chatdoctor\/llama-13b-32k-medqa-open-ir\/checkpoint-3500\/ir",
+    "triples": "\/future\/u\/okhattab\/root\/unit\/experiments\/2021.10\/downstream.distillation.round2.2_score\/round2.nway6.cosine.ib\/examples.64.json",
+    "collection": "\/future\/u\/okhattab\/data\/MSMARCO\/collection.tsv",
+    "queries": "\/future\/u\/okhattab\/data\/MSMARCO\/queries.train.tsv",
+    "index_name": null,
+    "overwrite": false,
+    "root": "\/future\/u\/okhattab\/root\/unit\/experiments",
+    "experiment": "2021.10",
+    "index_root": null,
+    "name": "kldR2.nway64.ib",
+    "rank": 0,
+    "nranks": 4,
+    "amp": true,
+    "gpus": 8,
+    "meta": {
+        "hostname": "gamma",
+        "git_branch": "main",
+        "git_hash": "58087227c8ead73499b761c7f7a569844d01d248",
+        "git_commit_datetime": "2023-10-16 12:32:12+08:00",
+        "current_datetime": "Apr 21, 2024 ; 12:29AM UTC (+0000)",
+        "cmd": "supervised-fine-tune2.py --model_name_or_path \/data\/experiment_data\/junda\/chatdoctor\/llama-13b-32k-medqa-open-reason-hf --colbert_path \/data\/experiment_data\/junda\/chatdoctor\/llama-13b-32k-medqa-open-ir\/checkpoint-3500\/ir --bf16 True --data_path error_20.json --output_dir \/data\/experiment_data\/junda\/chatdoctor\/llama-13b-32k-medqa-open-ir\/ --cache_dir \/home\/jwang\/.cache --model_max_length 32768 --use_flash_attn True --low_rank_training True --num_train_epochs 1 --per_device_train_batch_size 1 --per_device_eval_batch_size 2 --gradient_accumulation_steps 8 --save_strategy epoch --save_total_limit 5 --learning_rate 1e-5 --weight_decay 0.0 --warmup_steps 20 --lr_scheduler_type constant_with_warmup --logging_steps 1 --deepspeed ds_configs\/stage2.json --tf32 True",
+        "version": "colbert-v0.4"
+    }
+}

ir/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/data/experiment_data/junda/chatdoctor/llama-13b-32k-medqa-open-ir/checkpoint-3500/ir",
+  "architectures": [
+    "HF_ColBERT"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.33.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

ir/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b38715f09522dfa838bb852448ea9145767f60e6a4522be6429e88bbf30fb06
+size 2655739297

ir/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

ir/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d10407e9b78459c5bc4b14226e51ca0e084217025124a089d8bcc84ee4c5ffb
+size 9948731593

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89ccfb8f387243e3dedb0f48dfc53f5560aa6e9f31e96fdf586bca7bfc0c362e
+size 9904157328

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9a5dc574c097ddf4a4a757790df6e631074dda73340222d11fc3e59d246b63
+size 6617386045

pytorch_model.bin.index.json

@@ -0,0 +1,570 @@
+{
+  "metadata": {
+    "total_size": 26470071296
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.embeddings.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.embeddings.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.embeddings.position_embeddings.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.embeddings.token_type_embeddings.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.embeddings.word_embeddings.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.0.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.0.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.0.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.0.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.0.attention.self.key.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.0.attention.self.key.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.0.attention.self.query.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.0.attention.self.query.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.0.attention.self.value.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.0.attention.self.value.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.0.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.0.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.0.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.0.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.0.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.0.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.1.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.1.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.1.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.1.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.1.attention.self.key.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.1.attention.self.key.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.1.attention.self.query.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.1.attention.self.query.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.1.attention.self.value.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.1.attention.self.value.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.1.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.1.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.1.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.1.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.1.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.1.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.10.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.10.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.10.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.10.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.10.attention.self.key.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.10.attention.self.key.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.10.attention.self.query.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.10.attention.self.query.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.10.attention.self.value.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.10.attention.self.value.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.10.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.10.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.10.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.10.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.10.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.10.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.11.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.11.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.11.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.11.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.11.attention.self.key.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.11.attention.self.key.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.11.attention.self.query.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.11.attention.self.query.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.11.attention.self.value.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.11.attention.self.value.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.11.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.11.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.11.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.11.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.11.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.11.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.2.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.2.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.2.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.2.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.2.attention.self.key.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.2.attention.self.key.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.2.attention.self.query.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.2.attention.self.query.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.2.attention.self.value.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.2.attention.self.value.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.2.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.2.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.2.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.2.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.2.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.2.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.3.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.3.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.3.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.3.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.3.attention.self.key.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.3.attention.self.key.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.3.attention.self.query.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.3.attention.self.query.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.3.attention.self.value.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.3.attention.self.value.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.3.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.3.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.3.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.3.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.3.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.3.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.4.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.4.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.4.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.4.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.4.attention.self.key.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.4.attention.self.key.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.4.attention.self.query.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.4.attention.self.query.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.4.attention.self.value.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.4.attention.self.value.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.4.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.4.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.4.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.4.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.4.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.4.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.5.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.5.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.5.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.5.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.5.attention.self.key.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.5.attention.self.key.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.5.attention.self.query.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.5.attention.self.query.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.5.attention.self.value.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.5.attention.self.value.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.5.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.5.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.5.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.5.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.5.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.5.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.6.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.6.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.6.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.6.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.6.attention.self.key.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.6.attention.self.key.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.6.attention.self.query.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.6.attention.self.query.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.6.attention.self.value.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.6.attention.self.value.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.6.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.6.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.6.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.6.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.6.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.6.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.7.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.7.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.7.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.7.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.7.attention.self.key.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.7.attention.self.key.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.7.attention.self.query.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.7.attention.self.query.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.7.attention.self.value.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.7.attention.self.value.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.7.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.7.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.7.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.7.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.7.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.7.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.8.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.8.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.8.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.8.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.8.attention.self.key.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.8.attention.self.key.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.8.attention.self.query.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.8.attention.self.query.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.8.attention.self.value.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.8.attention.self.value.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.8.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.8.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.8.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.8.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.8.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.8.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.9.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.9.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.9.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.9.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.9.attention.self.key.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.9.attention.self.key.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.9.attention.self.query.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.9.attention.self.query.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.9.attention.self.value.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.9.attention.self.value.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.9.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.9.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.9.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.9.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.9.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.encoder.layer.9.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.pooler.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.bert.pooler.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.colbert.model.linear.weight": "pytorch_model-00003-of-00003.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
+  }
+}

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,37 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 32768,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}