Commit From AutoTrain

.gitattributes

@@ -32,3 +32,6 @@ 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
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,20 @@
+
+---
+tags:
+- autotrain
+- text-generation
+widget:
+- text: "I love AutoTrain because "
+datasets:
+- Metehan92/autotrain-data-q4oo-1wzg-vlx5
+co2_eq_emissions:
+  emissions: 0
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Generation
+- CO2 Emissions (in grams): 0.0000
+
+## Validation Metrics
+loss: nan

adapter_config.json

@@ -0,0 +1,16 @@
+{
+  "base_model_name_or_path": "EleutherAI/pythia-70m",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4f0724e500289ba1fde05418abcc29b56e701e465518cc8958fb8cd04ac957e
+size 791061

handler.py

@@ -0,0 +1,40 @@
+from typing import Dict, List, Any
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel, PeftConfig
+import torch
+
+
+class EndpointHandler:
+    def __init__(self, path=""):
+        # load model and processor from path
+        config = PeftConfig.from_pretrained(path)
+        model = AutoModelForCausalLM.from_pretrained(
+            config.base_model_name_or_path, torch_dtype=torch.float16, load_in_8bit=True, device_map="auto"
+        )
+        self.model = PeftModel.from_pretrained(model, path)
+        self.tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
+        self.model.eval()
+
+    def __call__(self, data: Dict[str, Any]) -> Dict[str, str]:
+        '''
+        Args:
+            data (:dict:):
+                The payload with the text prompt and generation parameters.
+        '''
+        # process input
+        inputs = data.pop("inputs", data)
+        parameters = data.pop("parameters", None)
+
+        # preprocess
+        input_ids = self.tokenizer(inputs, return_tensors="pt").input_ids
+
+        # pass inputs with all kwargs in data
+        if parameters is not None:
+            outputs = self.model.generate(input_ids=input_ids, **parameters)
+        else:
+            outputs = self.model.generate(input_ids=input_ids)
+
+        # postprocess the prediction
+        prediction = self.tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+        return [{"generated_text": prediction}]

requirements.txt

@@ -0,0 +1,5 @@
+accelerate==0.18.0
+transformers==4.28.1
+git+https://github.com/huggingface/peft.git
+bitsandbytes
+tokenizers>=0.13.3

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cf430678137c8491ca82fb7092ee49e44ad38857fffe1e4a4a5ed860139a5b8
+size 2113738

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}