add midm

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+adapter_model.bin filter=lfs diff=lfs merge=lfs -text
+midm_bitext_tokenizer.model filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -0,0 +1,24 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "KT-AI/midm-bitext-S-7B-inst-v1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_fc",
+    "c_proj",
+    "c_attn"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b27a7915ed209b363c7078b4e86f5fff5e7e26a57428d94772f3cdd942e4727
+size 67069130

midm_bitext_tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98789fa1bf89a1f9692889fb4a0029d3d096a9109cebf4f6bce1a255f2701378
+size 1457356

special_tokens_map.json

@@ -0,0 +1,12 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "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
+    },
+    "3": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "auto_map": {
+    "AutoTokenizer": [
+      "KT-AI/midm-bitext-S-7B-inst-v1--midm_bitext_tokenization.Midm_bitext_Tokenizer",
+      null
+    ]
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "Midm_bitext_Tokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.32,
+  "eval_steps": 500,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 9.972326633975752e-05,
+      "loss": 1.6982,
+      "step": 50
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.765191054744305e-05,
+      "loss": 1.0341,
+      "step": 100
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.363468755735123e-05,
+      "loss": 1.0017,
+      "step": 150
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 8.783564079088477e-05,
+      "loss": 1.0131,
+      "step": 200
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 8.049157449684723e-05,
+      "loss": 0.948,
+      "step": 250
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 7.190238384283412e-05,
+      "loss": 1.01,
+      "step": 300
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 6.241880868706075e-05,
+      "loss": 0.972,
+      "step": 350
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 5.242811110572242e-05,
+      "loss": 1.0579,
+      "step": 400
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.2338261534486844e-05,
+      "loss": 1.0209,
+      "step": 450
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 3.2561279283505883e-05,
+      "loss": 0.9866,
+      "step": 500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.349640771651611e-05,
+      "loss": 0.9984,
+      "step": 550
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.5513811136094787e-05,
+      "loss": 1.0059,
+      "step": 600
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 8.939459113251408e-06,
+      "loss": 0.9161,
+      "step": 650
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.041815510209396e-06,
+      "loss": 0.9191,
+      "step": 700
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.0208757505326016e-06,
+      "loss": 0.9088,
+      "step": 750
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0,
+      "loss": 0.944,
+      "step": 800
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 800,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 2.48413559980032e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92509cc597a20a019a773cf74244011a2ec436a68b233ea965ae6575d204128f
+size 4600