Upload 4 files

.gitattributes

@@ -33,3 +33,4 @@ 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
+FILTER_GREATERTHANTHREE_FROM_SHEETS_SMOTE_train.csv filter=lfs diff=lfs merge=lfs -text

Callback.py

@@ -0,0 +1,75 @@
+"""
+Helpers to support streaming generate output.
+Borrowed from https://github.com/oobabooga/text-generation-webui/blob/ad37f396fc8bcbab90e11ecf17c56c97bfbd4a9c/modules/callbacks.py
+"""
+
+import gc
+import traceback
+from queue import Queue
+from threading import Thread
+
+import torch
+import transformers
+
+
+class Stream(transformers.StoppingCriteria):
+    def __init__(self, callback_func=None):
+        self.callback_func = callback_func
+
+    def __call__(self, input_ids, scores) -> bool:
+        if self.callback_func is not None:
+            self.callback_func(input_ids[0])
+        return False
+
+
+class Iteratorize:
+
+    """
+    Transforms a function that takes a callback
+    into a lazy iterator (generator).
+    """
+
+    def __init__(self, func, kwargs={}, callback=None):
+        self.mfunc = func
+        self.c_callback = callback
+        self.q = Queue()
+        self.sentinel = object()
+        self.kwargs = kwargs
+        self.stop_now = False
+
+        def _callback(val):
+            if self.stop_now:
+                raise ValueError
+            self.q.put(val)
+
+        def gentask():
+            try:
+                ret = self.mfunc(callback=_callback, **self.kwargs)
+            except ValueError:
+                pass
+            except:
+                traceback.print_exc()
+                pass
+
+            self.q.put(self.sentinel)
+            if self.c_callback:
+                self.c_callback(ret)
+
+        self.thread = Thread(target=gentask)
+        self.thread.start()
+
+    def __iter__(self):
+        return self
+
+    def __next__(self):
+        obj = self.q.get(True, None)
+        if obj is self.sentinel:
+            raise StopIteration
+        else:
+            return obj
+
+    def __enter__(self):
+        return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        self.stop_now = True

FILTER_GREATERTHANTHREE_FROM_SHEETS_SMOTE_train.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe0b99be053bfc84bbe4afcc05fe39f90c149427c14fa5551d2b3505a80a443e
+size 24859949

Prompter.py

@@ -0,0 +1,45 @@
+import json
+import os.path as osp
+from typing import Union
+class Prompter(object):
+    __slots__ = ("template", "_verbose")
+
+    def __init__(self, template_name: str = "", verbose: bool = False):
+        self._verbose = verbose
+        if not template_name:
+            # Enforce the default here, so the constructor can be called with '' and will not break.
+            template_name = "alpaca"
+        file_name = osp.join("templates", f"{template_name}.json")
+        if not osp.exists(file_name):
+            raise ValueError(f"Can't read {file_name}")
+        with open(file_name) as fp:
+            self.template = json.load(fp)
+        if self._verbose:
+            print(
+                f"Using prompt template {template_name}: {self.template['description']}"
+            )
+
+    def generate_prompt(
+        self,
+        instruction: str,
+        input: Union[None, str] = None,
+        label: Union[None, str] = None,
+    ) -> str:
+        # returns the full prompt from instruction and optional input
+        # if a label (=response, =output) is provided, it's also appended.
+        if input:
+            res = self.template["prompt_input"].format(
+                instruction=instruction, input=input
+            )
+        else:
+            res = self.template["prompt_no_input"].format(
+                instruction=instruction
+            )
+        if label:
+            res = f"{res}{label}"
+        if self._verbose:
+            print(res)
+        return res
+
+    def get_response(self, output: str) -> str:
+        return output.split(self.template["response_split"])[1].strip()

templates/alpaca.json

@@ -0,0 +1,6 @@
+{
+    "description": "Template used by Alpaca-LoRA.",
+    "prompt_input": "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Input:\n{input}\n\n### Response:\n",
+    "prompt_no_input": "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response:\n",
+    "response_split": "### Response:"    
+}