First model version

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyPixel/Llama-2-7B-bf16-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc09f091cb6ec6007e7ab66374168d66bdf1a83fd9ee12fcbd035823f41c7286
+size 33571624

handler.py

@@ -0,0 +1,31 @@
+from typing import  Dict, List, Any
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+import torch
+from peft import PeftModel
+import json
+import os
+
+
+class EndpointHandler():
+    def __init__(self, path=""):
+        base_model_path = json.load(open(os.path.join(path, "training_params.json")))["model"]
+        model = AutoModelForCausalLM.from_pretrained(
+            base_model_path,
+            torch_dtype=torch.float16,
+            low_cpu_mem_usage=True,
+            trust_remote_code=True,
+            device_map="auto",
+        )
+        tokenizer = AutoTokenizer.from_pretrained(base_model_path, trust_remote_code=True)
+        model = PeftModel.from_pretrained(model, path)
+        model = model.merge_and_unload()
+        self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+    def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
+        inputs = data.pop("inputs", data)
+        parameters = data.pop("parameters", None)
+        if parameters is not None:
+            prediction = self.pipeline(inputs, **parameters)
+        else:
+            prediction = self.pipeline(inputs)
+        return prediction

requirements.txt

@@ -0,0 +1,2 @@
+peft==0.7.1
+transformers==4.36.1

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ed40eada62ed18d510ce6399763cf7bae0c21e1c434756a47bc7348a976b727
+size 4664

training_params.json

@@ -0,0 +1,48 @@
+{
+    "model": "TinyPixel/Llama-2-7B-bf16-sharded",
+    "project_name": "Test",
+    "data_path": "oivlisnet/Test",
+    "train_split": "train",
+    "valid_split": null,
+    "add_eos_token": false,
+    "block_size": -1,
+    "model_max_length": 2048,
+    "padding": null,
+    "trainer": "sft",
+    "use_flash_attention_2": false,
+    "log": "none",
+    "disable_gradient_checkpointing": false,
+    "logging_steps": -1,
+    "evaluation_strategy": "epoch",
+    "save_total_limit": 1,
+    "save_strategy": "epoch",
+    "auto_find_batch_size": false,
+    "mixed_precision": null,
+    "lr": 0.0002,
+    "epochs": 3,
+    "batch_size": 2,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "apply_chat_template": false,
+    "quantization": "int4",
+    "target_modules": null,
+    "merge_adapter": false,
+    "peft": true,
+    "lora_r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "model_ref": null,
+    "dpo_beta": 0.1,
+    "prompt_text_column": "prompt",
+    "text_column": "text",
+    "rejected_text_column": "rejected",
+    "push_to_hub": false,
+    "repo_id": null,
+    "username": null,
+    "token": null
+}