Super-squash branch 'main' using huggingface_hub

Co-authored-by: SFconvertbot <[email protected]>
Co-authored-by: 3v324v23 <[email protected]>

.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
+*.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
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,211 @@
+---
+license:
+- apache-2.0
+- cc-by-nc-4.0
+datasets: pszemraj/fleece2instructions-codealpaca
+tags:
+- generated_from_trainer
+- instruct
+- instructions
+- code
+- instructiongen
+metrics:
+- rouge
+language:
+- en
+widget:
+- text: |
+    git lfs install
+    huggingface-cli lfs-enable-largefiles .
+    git lfs track "*.bin"
+    git add .
+    git commit -a -m "add fp32 chkpt"
+    git push
+  example_title: bash
+- text: |
+    export interface DocumentParams {
+      pageContent: string;
+
+      // eslint-disable-next-line @typescript-eslint/no-explicit-any
+      metadata: Record<string, any>;
+    }
+
+    /**
+     * Interface for interacting with a document.
+     */
+    export class Document implements DocumentParams {
+      pageContent: string;
+
+      // eslint-disable-next-line @typescript-eslint/no-explicit-any
+      metadata: Record<string, any>;
+
+      constructor(fields?: Partial<DocumentParams>) {
+        this.pageContent = fields?.pageContent ?? this.pageContent;
+        this.metadata = fields?.metadata ?? {};
+      }
+    }
+  example_title: js
+- text: |
+    def merge(left, right):
+        if len(left) == 0:
+            return right
+
+        if len(right) == 0:
+            return left
+
+        result = []
+        index_left = index_right = 0
+
+        while len(result) < len(left) + len(right):
+            if left[index_left] <= right[index_right]:
+                result.append(left[index_left])
+                index_left += 1
+            else:
+                result.append(right[index_right])
+                index_right += 1
+
+            if index_right == len(right):
+                result += left[index_left:]
+                break
+
+            if index_left == len(left):
+                result += right[index_right:]
+                break
+
+        return result
+  example_title: merge
+- text: >
+    import pandas as pd
+
+    import plotly.graph_objects as go
+
+
+    df =
+    pd.read_csv('https://raw.githubusercontent.com/plotly/datasets/master/2014_apple_stock.csv')
+
+
+    fig = go.Figure(go.Scatter(x = df['AAPL_x'], y = df['AAPL_y'],
+                      name='Share Prices (in USD)'))
+
+    fig.update_layout(title='Apple Share Prices over time (2014)',
+                       plot_bgcolor='rgb(230, 230,230)',
+                       showlegend=True)
+
+    fig.show()
+  example_title: plot
+- text: |
+    from spellchecker import SpellChecker
+
+    spell = SpellChecker()
+
+    def check_word_spelling(word: str):
+        misspelled = spell.unknown([word])
+        return len(misspelled) == 0
+
+    def eval_and_replace(text: str, match_token: str = "- "):
+        if match_token not in text:
+            return text
+        else:
+            while True:
+                full_before_text = text.split(match_token, maxsplit=1)[0]
+                before_text = [
+                    char for char in full_before_text.split()[-1] if char.isalpha()
+                ]
+                before_text = "".join(before_text)
+                full_after_text = text.split(match_token, maxsplit=1)[-1]
+                after_text = [char for char in full_after_text.split()[0] if char.isalpha()]
+                after_text = "".join(after_text)
+                full_text = before_text + after_text
+                if check_word_spelling(full_text):
+                    text = full_before_text + full_after_text
+                else:
+                    text = full_before_text + " " + full_after_text
+                if match_token not in text:
+                    break
+            return text
+
+    text = "I- am- a go- od- boy"
+    eval_and_replace(text)
+  example_title: spell check
+- text: >
+    import torch
+
+    from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+
+    checkpoint = "distilbert-base-uncased-finetuned-sst-2-english"
+
+    tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+
+    model = AutoModelForSequenceClassification.from_pretrained(checkpoint)
+
+    sequences = ["I've been waiting for a HuggingFace course my whole life.",
+    "So have I!"]
+
+
+    tokens = tokenizer(sequences, padding=True, truncation=True,
+    return_tensors="pt")
+
+    output = model(**tokens)
+  example_title: model inference
+inference:
+  parameters:
+    max_length: 96
+    num_beams: 4
+---
+
+
+# bart-large-code-instructiongen
+
+Use this text2text model to find out what LLM instructions might be able to generate an arbitary piece of code!
+
+- Check out a [basic demo on Spaces](https://huggingface.co/spaces/pszemraj/generate-instructions)
+- An example of how to use instructiongen models in a CLI script can be found [here](https://gist.github.com/pszemraj/8b0213e700763106074d3ac15d041c14)
+- You can find other models fine-tuned for instruction generation by [searching for the instructiongen tag](https://huggingface.co/models?other=instructiongen)
+
+## about 
+
+This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on the `pszemraj/fleece2instructions-codealpaca` dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9222
+- Rouge1: 62.0692
+- Rouge2: 36.1947
+- Rougel: 57.5128
+- Rougelsum: 58.6613
+- Gen Len: 31.0060
+
+
+## Intended uses & limitations
+
+🚨 **note:** as the authors elected to release the [original dataset](https://github.com/sahil280114/codealpaca) under `cc-by-nc`, the license carries over to this model and **cannot be used for commercial activity**. 
+
+Intended use: Research on domain adaptation and/or other improvements to LLMs by extending instruction:text data pairs.
+
+## Training and evaluation data
+
+Refer to the linked dataset card for `pszemraj/fleece2instructions-codealpaca` or the [original dataset](https://github.com/sahil280114/codealpaca) repo.
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 6e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| 1.0914        | 1.0   | 563  | 1.0303          | 60.288  | 34.1884 | 55.9293 | 57.0714   | 30.6267 |
+| 0.8688        | 2.0   | 1126 | 0.9333          | 61.0409 | 34.9823 | 56.4887 | 57.6662   | 31.7255 |
+| 0.6773        | 3.0   | 1689 | 0.9222          | 62.0692 | 36.1947 | 57.5128 | 58.6613   | 31.0060 |

config.json

@@ -0,0 +1,74 @@
+{
+  "_name_or_path": "pszemraj/bart-large-fleece2instructions-codealpaca-r1",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.3",
+  "use_cache": true,
+  "vocab_size": 50265
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "max_length": 96,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.27.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b04741a2fc6352f31bd138dfd4d9c6b0d8f50d759bc8f5cec610463976df0725
+size 1625426996

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc2135c478fffaa668b32883b38b3cab833c38f304f43082c9921d9ebd005257
+size 1625534221

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}