Upload folder using huggingface_hub

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

dataset_num_samples.json

@@ -0,0 +1 @@
+{"e5_train_ds_gpt4-retrieval_format.jsonl": 166602, "e5_train_ds_trivia_format.jsonl": 60296, "e5_train_ds_nli_format.jsonl": 275601, "e5_train_ds_gpt4-p2p_format.jsonl": 16842, "e5_train_ds_miracl_format.jsonl": 40203, "e5_train_ds_dureader_format.jsonl": 86395, "e5_train_ds_gpt4-p2s_format.jsonl": 121878, "e5_train_ds_fever_format.jsonl": 71257, "e5_train_ds_eli5_format.jsonl": 50293, "e5_train_ds_gpt4-s2s_format.jsonl": 13481, "e5_train_ds_msmarco-doc_format.jsonl": 71564, "e5_train_ds_t2ranking_format.jsonl": 112335, "e5_train_ds_quora_format.jsonl": 14926, "e5_train_ds_mrtydi_format.jsonl": 48729, "e5_train_ds_nq_format.jsonl": 71408, "e5_train_ds_squad_format.jsonl": 87599, "e5_train_ds_msmarco_format.jsonl": 244582, "e5_train_ds_s2orc_format.jsonl": 80000, "e5_train_ds_gpt4-bitext_format.jsonl": 89324, "e5_train_ds_gpt4-sts_format.jsonl": 98626, "e5_train_ds_hotpotqa_format.jsonl": 68659}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:549d34aed69346a1c8ff5bcf8871b70b7a8e8aae41d47eeedfc23c6fe8646bfa
+size 14221467522

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": "<s>",
+  "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d51e4a2f4a51b3f010f1ebbba500cd19c50574529318aed5d0b86eb49a1a0df0
+size 5048