Super-squash branch 'main' using huggingface_hub

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,273 @@
+---
+license: apache-2.0
+datasets:
+- BEE-spoke-data/pypi_clean-deduped
+source_model: BEE-spoke-data/smol_llama-101M-GQA
+language:
+- en
+tags:
+- python
+- codegen
+- markdown
+- smol_llama
+metrics:
+  - accuracy
+inference:
+  parameters:
+    max_new_tokens: 48
+    min_new_tokens: 8
+    num_beams: 3
+    early_stopping: true
+    repetition_penalty: 1.1
+    no_repeat_ngram_size: 6
+    renormalize_logits: true
+widget:
+  - text: |
+      def add_numbers(a, b):
+          return
+    example_title: Add Numbers Function
+  - text: |
+      class Car:
+          def __init__(self, make, model):
+              self.make = make
+              self.model = model
+
+          def display_car(self):
+    example_title: Car Class
+  - text: |
+      import pandas as pd
+      data = {'Name': ['Tom', 'Nick', 'John'], 'Age': [20, 21, 19]}
+      df = pd.DataFrame(data).convert_dtypes()
+      # eda
+      
+    example_title: Pandas DataFrame
+  - text: |
+      def factorial(n):
+          if n == 0:
+              return 1
+          else:
+    example_title: Factorial Function
+  - text: |
+      def fibonacci(n):
+          if n <= 0:
+              raise ValueError("Incorrect input")
+          elif n == 1:
+              return 0
+          elif n == 2:
+              return 1
+          else:
+    example_title: Fibonacci Function
+  - text: |
+      import matplotlib.pyplot as plt
+      import numpy as np
+      x = np.linspace(0, 10, 100)
+      # simple plot
+      
+    example_title: Matplotlib Plot
+  - text: |
+      def reverse_string(s:str) -> str:
+          return
+    example_title: Reverse String Function
+  - text: |
+      def is_palindrome(word:str) -> bool:
+          return
+    example_title: Palindrome Function
+  - text: |
+      def bubble_sort(lst: list):
+          n = len(lst)
+          for i in range(n):
+              for j in range(0, n-i-1):
+    example_title: Bubble Sort Function
+  - text: |
+      def binary_search(arr, low, high, x):
+          if high >= low:
+              mid = (high + low) // 2
+              if arr[mid] == x:
+                  return mid
+              elif arr[mid] > x:
+    example_title: Binary Search Function
+---
+
+# smol_llama-101M-GQA: python
+
+<a href="https://colab.research.google.com/gist/pszemraj/91b5a267df95461b46922e6c0212e8f7/beecoder-basic-test-notebook.ipynb">
+  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
+</a>
+
+> 400MB of buzz: pure Python programming nectar! 🍯
+
+This model is the general pre-trained checkpoint `BEE-spoke-data/smol_llama-101M-GQA` trained on a deduped version of `pypi` for +1 epoch. Play with the model in [this demo space](https://huggingface.co/spaces/BEE-spoke-data/beecoder-playground).
+
+- Its architecture is the same as the base, with some new Python-related tokens added to vocab prior to training.
+- It can generate basic Python code and markdown in README style, but will struggle with harder planning/reasoning tasks
+- This is an experiment to test the abilities of smol-sized models in code generation; meaning **both** its capabilities and limitations
+
+Use with care & understand that there may be some bugs 🐛 still to be worked out.
+
+## Usage 
+
+📌 Be sure to note:
+
+1. The model uses the "slow" llama2 tokenizer. Set use_fast=False when loading the tokenizer.
+2. Use transformers library version 4.33.3 due to a known issue in version 4.34.1 (_at time of writing_)
+
+> Which llama2 tokenizer the API widget uses is an age-old mystery, and may cause minor whitespace issues (widget only).
+
+To install the necessary packages and load the model:
+
+```python
+# Install necessary packages
+# pip install transformers==4.33.3 accelerate sentencepiece
+
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+# Load the tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained(
+    "BEE-spoke-data/smol_llama-101M-GQA-python",
+    use_fast=False,
+)
+model = AutoModelForCausalLM.from_pretrained(
+    "BEE-spoke-data/smol_llama-101M-GQA-python",
+    device_map="auto",
+)
+
+# The model can now be used as any other decoder
+```
+
+### longer code-gen example
+
+
+Below is a quick script that can be used as a reference/starting point for writing your own, better one :)
+
+
+
+<details>
+<summary>🔥 Unleash the Power of Code Generation! Click to Reveal the Magic! 🔮</summary>
+
+Are you ready to witness the incredible possibilities of code generation? 🚀. Brace yourself for an exceptional journey into the world of artificial intelligence and programming. Observe a script that will change the way you create and finalize code.
+
+This script provides entry to a planet where machines can write code with remarkable precision and imagination. 
+
+```python
+"""
+simple script for testing model(s) designed to generate/complete code
+
+See details/args with the below. 
+    python textgen_inference_code.py --help
+"""
+import logging
+import random
+import time
+from pathlib import Path
+
+import fire
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+logging.basicConfig(format="%(levelname)s - %(message)s", level=logging.INFO)
+
+
+class Timer:
+    """
+    Basic timer utility.
+    """
+
+    def __enter__(self):
+
+        self.start_time = time.perf_counter()
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+
+        self.end_time = time.perf_counter()
+        self.elapsed_time = self.end_time - self.start_time
+        logging.info(f"Elapsed time: {self.elapsed_time:.4f} seconds")
+
+
+def load_model(model_name, use_fast=False):
+    """ util for loading model and tokenizer"""
+    logging.info(f"Loading model: {model_name}")
+    tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=use_fast)
+    model = AutoModelForCausalLM.from_pretrained(
+        model_name, torch_dtype="auto", device_map="auto"
+    )
+    model = torch.compile(model)
+    return tokenizer, model
+
+
+def run_inference(prompt, model, tokenizer, max_new_tokens: int = 256):
+    """
+    run_inference
+
+    Args:
+        prompt (TYPE): Description
+        model (TYPE): Description
+        tokenizer (TYPE): Description
+        max_new_tokens (int, optional): Description
+
+    Returns:
+        TYPE: Description
+    """
+    logging.info(f"Running inference with max_new_tokens={max_new_tokens} ...")
+    with Timer() as timer:
+        inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+        outputs = model.generate(
+            **inputs,
+            max_new_tokens=max_new_tokens,
+            min_new_tokens=8,
+            renormalize_logits=True,
+            no_repeat_ngram_size=8,
+            repetition_penalty=1.04,
+            num_beams=4,
+            early_stopping=True,
+        )
+    text = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
+    logging.info(f"Output text:\n\n{text}")
+    return text
+
+
+def main(
+    model_name="BEE-spoke-data/smol_llama-101M-GQA-python",
+    prompt:str=None,
+    use_fast=False,
+    n_tokens: int = 256,
+):
+    """Summary
+
+    Args:
+        model_name (str, optional): Description
+        prompt (None, optional): specify the prompt directly (default: random choice from list)
+        n_tokens (int, optional): max new tokens to generate
+    """
+    logging.info(f"Inference with:\t{model_name}, max_new_tokens:{n_tokens}")
+
+    if prompt is None:
+        prompt_list = [
+            '''
+            def print_primes(n: int):
+               """
+               Print all primes between 1 and n
+               """''',
+            "def quantum_analysis(",
+            "def sanitize_filenames(target_dir:str, recursive:False, extension",
+        ]
+        prompt = random.SystemRandom().choice(prompt_list)
+
+    logging.info(f"Using prompt:\t{prompt}")
+
+    tokenizer, model = load_model(model_name, use_fast=use_fast)
+
+    run_inference(prompt, model, tokenizer, n_tokens)
+
+
+if __name__ == "__main__":
+    fire.Fire(main)
+```
+
+Wowoweewa!! It can create some file cleaning utilities.
+
+
+</details>
+
+
+---

added_tokens.json

@@ -0,0 +1,84 @@
+{
+  "**kwargs": 32000,
+  "*args": 32026,
+  "<0x0A><0x0A>": 32070,
+  "<0x0A><0x0A><0x0A>": 32071,
+  ">>> ": 32036,
+  "@abstractmethod": 32001,
+  "@classmethod": 32002,
+  "@property": 32003,
+  "@staticmethod": 32004,
+  "AttributeError": 32038,
+  "Callable": 32039,
+  "DELETE": 32030,
+  "GraphQL": 32027,
+  "ImportError": 32040,
+  "JOIN": 32031,
+  "JWT": 32028,
+  "KeyError": 32041,
+  "NotImplementedError": 32042,
+  "Notes": 32035,
+  "OAuth": 32029,
+  "README": 32043,
+  "Raises": 32037,
+  "RuntimeError": 32044,
+  "TODO": 32034,
+  "Tuple": 32045,
+  "TypeError": 32046,
+  "ValueError": 32047,
+  "__all__": 32005,
+  "__call__": 32006,
+  "__class__": 32007,
+  "__contains__": 32008,
+  "__del__": 32010,
+  "__delitem__": 32009,
+  "__dict__": 32011,
+  "__doc__": 32012,
+  "__file__": 32013,
+  "__future__": 32014,
+  "__getitem__": 32015,
+  "__init__": 32016,
+  "__len__": 32017,
+  "__main__": 32018,
+  "__name__": 32019,
+  "__package__": 32020,
+  "__props__": 32021,
+  "__repr__": 32022,
+  "__self__": 32023,
+  "__setitem__": 32024,
+  "__str__": 32025,
+  "asyncio": 32048,
+  "cuda": 32051,
+  "dtype": 32049,
+  "finally": 32050,
+  "functools": 32052,
+  "gRPC": 32032,
+  "getattr": 32053,
+  "getter": 32054,
+  "globals()": 32068,
+  "hasattr": 32055,
+  "itertools": 32056,
+  "jsii": 32057,
+  "locals()": 32067,
+  "pathlib": 32058,
+  "pickle": 32061,
+  "plt": 32059,
+  "pulumi": 32060,
+  "rtype": 32033,
+  "setter": 32062,
+  "shutil": 32063,
+  "sklearn": 32064,
+  "stderr": 32065,
+  "torch": 32066,
+  "yield": 32069,
+  "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 32072,
+  "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 32073,
+  "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 32074,
+  "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 32075,
+  "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 32076,
+  "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 32077,
+  "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 32078,
+  "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 32079,
+  "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 32080,
+  "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 32081
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "pszemraj/smol_llama-101M-GQA-python",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 1024,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 6,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.33.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2c5e483eb866eef74eeebbd62608fa5843d6ab17b45be4883aa6b8ff8fc6abe
+size 405058720

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "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 +1,719 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "**kwargs",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32001": {
+      "content": "@abstractmethod",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32002": {
+      "content": "@classmethod",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32003": {
+      "content": "@property",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32004": {
+      "content": "@staticmethod",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32005": {
+      "content": "__all__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32006": {
+      "content": "__call__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32007": {
+      "content": "__class__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32008": {
+      "content": "__contains__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32009": {
+      "content": "__delitem__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32010": {
+      "content": "__del__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32011": {
+      "content": "__dict__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32012": {
+      "content": "__doc__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32013": {
+      "content": "__file__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32014": {
+      "content": "__future__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32015": {
+      "content": "__getitem__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32016": {
+      "content": "__init__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32017": {
+      "content": "__len__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32018": {
+      "content": "__main__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32019": {
+      "content": "__name__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32020": {
+      "content": "__package__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32021": {
+      "content": "__props__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32022": {
+      "content": "__repr__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32023": {
+      "content": "__self__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32024": {
+      "content": "__setitem__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32025": {
+      "content": "__str__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32026": {
+      "content": "*args",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": false
+    },
+    "32027": {
+      "content": "GraphQL",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32028": {
+      "content": "JWT",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32029": {
+      "content": "OAuth",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32030": {
+      "content": "DELETE",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32031": {
+      "content": "JOIN",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32032": {
+      "content": "gRPC",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32033": {
+      "content": "rtype",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32034": {
+      "content": "TODO",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32035": {
+      "content": "Notes",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32036": {
+      "content": ">>> ",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32037": {
+      "content": "Raises",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32038": {
+      "content": "AttributeError",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32039": {
+      "content": "Callable",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32040": {
+      "content": "ImportError",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32041": {
+      "content": "KeyError",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32042": {
+      "content": "NotImplementedError",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32043": {
+      "content": "README",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32044": {
+      "content": "RuntimeError",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32045": {
+      "content": "Tuple",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32046": {
+      "content": "TypeError",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32047": {
+      "content": "ValueError",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32048": {
+      "content": "asyncio",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32049": {
+      "content": "dtype",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32050": {
+      "content": "finally",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32051": {
+      "content": "cuda",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32052": {
+      "content": "functools",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32053": {
+      "content": "getattr",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32054": {
+      "content": "getter",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32055": {
+      "content": "hasattr",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32056": {
+      "content": "itertools",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32057": {
+      "content": "jsii",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32058": {
+      "content": "pathlib",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32059": {
+      "content": "plt",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32060": {
+      "content": "pulumi",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32061": {
+      "content": "pickle",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32062": {
+      "content": "setter",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32063": {
+      "content": "shutil",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32064": {
+      "content": "sklearn",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32065": {
+      "content": "stderr",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32066": {
+      "content": "torch",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32067": {
+      "content": "locals()",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32068": {
+      "content": "globals()",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32069": {
+      "content": "yield",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32070": {
+      "content": "<0x0A><0x0A>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32071": {
+      "content": "<0x0A><0x0A><0x0A>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32072": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32073": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32074": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32075": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32076": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32077": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32078": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32079": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32080": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32081": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": 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
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}