Upload 8 files

adapter_config (1).json

@@ -0,0 +1,23 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "TheBloke/Llama-2-7B-fp16",
+  "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": 16,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model (1).bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a6063bcc5c9f35f9e5aebebd5ed4e429befc4fb08645b34fc43292e823c851
+size 67201357

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+    "pad_token_id": 0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "temperature": 0.5,
+    "top_p": 0.9,
+    "top_k": 30,
+    "do_sample": true,
+    "max_new_tokens": 3584,
+    "num_beams": 1,
+    "repetition_penalty": 1.2,
+    "no_repeat_ngram_size": 15
+}

gitattributes

@@ -0,0 +1,37 @@
+*.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
+*.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_model.bin filter=lfs diff=lfs merge=lfs -text
+tokenizer.model filter=lfs diff=lfs merge=lfs -text

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<unk>",
+  "sep_token": "<s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+    "tokenizer_class": "LlamaTokenizer",
+    "model_max_length": 4096,
+    "padding_side": "left",
+    "bos_token": "<s>",
+    "eos_token": "</s>",
+    "unk_token": "<unk>",
+    "clean_up_tokenization_spaces": false,
+    "special_tokens_map_file": "special_tokens_map.json"
+}

training_config.json

@@ -0,0 +1,35 @@
+{
+    "trainer": {
+        "evaluation_strategy": "steps",
+        "per_device_train_batch_size": 1,
+        "per_device_eval_batch_size": 1,
+        "gradient_accumulation_steps": 128,
+        "eval_steps": 50,
+        "save_steps": 50,
+        "logging_steps": 2,
+        "learning_rate": 0.0003,
+        "num_train_epochs": 5,
+        "lr_scheduler_type": "cosine",
+        "warmup_steps": 50,
+        "fp16": false,
+        "bf16": true,
+        "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": "internal_prompts/saiga_v2.json",
+    "model_name": "models/llama2-7b",
+    "model_type": "causal",
+    "max_tokens_count": 4096
+}
+