Update README.md

README.md

@@ -1,12 +1,115 @@
 ---
-license: apache-2.0
+license:
+- apache-2.0
+- cc-by-nc-4.0
+datasets: pszemraj/fleece2instructions-codealpaca
 tags:
-- generated_from_trainer
+  - generated_from_trainer
+  - instruct
+  - instructions
+  - code
 metrics:
-- rouge
-model-index:
-- name: bart-base-code-instructiongen
-  results: []
+  - rouge
+language:
+  - en
+widget:
+  - 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: Example One
+  - text: >
+      import torch
+
+      from tqdm.auto import tqdm
+
+
+      device = torch.device("cuda") if torch.cuda.is_available() else
+      torch.device("cpu")
+
+      model.to(device)
+
+
+      progress_bar = tqdm(range(num_training_steps))
+
+
+      model.train()
+
+      for epoch in range(num_epochs):
+          for batch in train_dataloader:
+              batch = {k: v.to(device) for k, v in batch.items()}
+              outputs = model(**batch)
+              loss = outputs.loss
+              loss.backward()
+
+              optimizer.step()
+              lr_scheduler.step()
+              optimizer.zero_grad()
+              progress_bar.update(1)
+    example_title: Example Two
+  - text: |
+      import evaluate
+
+      metric = evaluate.load("glue", "mrpc")
+      model.eval()
+      for batch in eval_dataloader:
+          batch = {k: v.to(device) for k, v in batch.items()}
+          with torch.no_grad():
+              outputs = model(**batch)
+
+          logits = outputs.logits
+          predictions = torch.argmax(logits, dim=-1)
+          metric.add_batch(predictions=predictions, references=batch["labels"])
+
+      metric.compute()
+    example_title: Example Three
+  - 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: Example Four
+  - 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: Example Five
 inference:
   parameters:
     max_length: 128
@@ -14,11 +117,11 @@ inference:
 
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
 
 # bart-base-code-instructiongen
 
+Use this text2text model to find out what LLM instructions might be able to generate an arbitary piece of code!
+
 This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the `pszemraj/fleece2instructions-codealpaca` dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.0136
@@ -28,17 +131,15 @@ It achieves the following results on the evaluation set:
 - Rougelsum: 56.9064
 - Gen Len: 29.7146
 
-## Model description
-
-More information needed
-
 ## Intended uses & limitations
 
-More information needed
+🚨 **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 `pszemraj/fleece2instructions-codealpaca`
+Refer to the linked dataset card for `pszemraj/fleece2instructions-codealpaca` or the [original dataset](https://github.com/sahil280114/codealpaca) repo.
 
 ## Training procedure
 
@@ -64,11 +165,3 @@ The following hyperparameters were used during training:
 | 1.1165        | 1.0   | 281  | 1.1090          | 57.9239 | 31.9259 | 53.8737 | 54.9811   | 28.2924 |
 | 1.0763        | 2.0   | 563  | 1.0267          | 59.9605 | 34.0298 | 55.7523 | 56.8021   | 29.6966 |
 | 0.9595        | 2.99  | 843  | 1.0136          | 59.9513 | 33.9118 | 55.7815 | 56.9064   | 29.7146 |
-
-
-### Framework versions
-
-- Transformers 4.28.0.dev0
-- Pytorch 2.0.0.dev20230212+cu118
-- Datasets 2.9.0
-- Tokenizers 0.13.2