Initial commit

.gitattributes

@@ -32,3 +32,5 @@ 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
+tokenizer.model filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -0,0 +1,19 @@
+{
+  "base_model_name_or_path": "huggyllama/llama-13b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2361fe144529c5c06e8b333e5aaffc836ccf6da69a850427fe03c87c454c3acc
+size 104973389

generation_config.json

@@ -0,0 +1,14 @@
+{
+    "pad_token_id": 0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "temperature": 1.0,
+    "top_p": 0.9,
+    "top_k": 30,
+    "do_sample": true,
+    "max_new_tokens": 1024,
+    "num_beams": 2,
+    "repetition_penalty": 1.1,
+    "no_repeat_ngram_size": 8
+}
+

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "sep_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "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 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 2048,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "models/llama-13b/special_tokens_map.json",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_config.json

@@ -0,0 +1,35 @@
+{
+    "trainer": {
+        "evaluation_strategy": "steps",
+        "per_device_train_batch_size": 4,
+        "per_device_eval_batch_size": 4,
+        "gradient_accumulation_steps": 32,
+        "eval_steps": 50,
+        "save_steps": 50,
+        "logging_steps": 5,
+        "learning_rate": 0.0003,
+        "num_train_epochs": 5,
+        "lr_scheduler_type": "cosine",
+        "warmup_steps": 30,
+        "fp16": true,
+        "bf16": false,
+        "torch_compile": false,
+        "optim": "adamw_torch"
+    },
+    "lora": {
+        "r": 16,
+        "lora_alpha": 16,
+        "lora_dropout": 0.05,
+        "bias": "none",
+        "target_modules": ["q_proj", "v_proj", "k_proj", "o_proj"],
+        "task_type": "CAUSAL_LM"
+    },
+    "load_in_8bit": true,
+    "only_target_loss": true,
+    "mode": "chat",
+    "templates_path": "ru_saiga_template.json",
+    "model_name": "models/llama-13b",
+    "model_type": "causal",
+    "max_tokens_count": 1024
+}
+