updated .gitignore for ch07/01 artefacts (#242)

* fixed markdown

* removed redundant imports

* updated .gitignore for ch07/01 artefacts

.gitignore

@@ -18,6 +18,10 @@ ch06/01_main-chapter-code/accuracy-plot.pdf
 
 ch07/01_main-chapter-code/loss-plot.pdf
 ch07/01_main-chapter-code/loss-plot-standalone.pdf
+ch07/01_main-chapter-code/loss-plot-baseline.pdf
+ch07/01_main-chapter-code/loss-plot-mask-instructions.pdf
+ch07/01_main-chapter-code/loss-plot-phi3-prompt.pdf
+ch07/01_main-chapter-code/loss-plot-alpaca52k.pdf
 
 # Checkpoint files
 appendix-A/01_main-chapter-code/model.pth
@@ -34,6 +38,11 @@ ch06/01_main-chapter-code/gpt2
 ch06/02_bonus_additional-experiments/gpt2
 ch06/03_bonus_imdb-classification/gpt2
 
+ch07/01_main-chapter-code/gpt2-medium355M-sft-baseline.pth
+ch07/01_main-chapter-code/gpt2-medium355M-sft-mask-instructions.pth
+ch07/01_main-chapter-code/gpt2-medium355M-sft-phi3-prompt.pth
+ch07/01_main-chapter-code/gpt2-medium355M-sft-alpaca52k.pth
+ch07/01_main-chapter-code/gpt2-medium355M-sft-lora.pth
 ch07/01_main-chapter-code/gpt2-medium355M-sft.pth
 ch07/01_main-chapter-code/gpt2-medium355M-sft-standalone.pth
 ch07/01_main-chapter-code/Smalltestmodel-sft-standalone.pth
@@ -71,6 +80,10 @@ ch06/03_bonus_imdb-classification/validation.csv
 ch07/01_main-chapter-code/instruction-data-with-response-standalone.json
 ch07/01_main-chapter-code/instruction-data-with-response-baseline.json
 ch07/01_main-chapter-code/instruction-data-with-response-mask-instructions.json
+ch07/01_main-chapter-code/loss-plot-lora.pdf
+ch07/01_main-chapter-code/instruction-data-with-response-alpaca52k.json
+ch07/01_main-chapter-code/instruction-data-with-response-lora.json
+ch07/01_main-chapter-code/instruction-data-with-response-phi3-prompt.json
 ch07/02_dataset-utilities/instruction-examples-modified.json
 
 # Temporary OS-related files

ch07/01_main-chapter-code/exercise-solutions.ipynb

@@ -43,7 +43,7 @@
    "source": [
     "Suppose we have the following data entry:\n",
     "\n",
-    "```\n",
+    "```json\n",
     "{\n",
     "  \"instruction\": \"Identify the correct spelling of the following word.\",\n",
     "  \"input\": \"Ocassion\",\n",
@@ -195,24 +195,24 @@
    "metadata": {},
    "source": [
     "```python\n",
-    "    for i, entry in tqdm(enumerate(test_data), total=len(test_data)):\n",
+    "for i, entry in tqdm(enumerate(test_data), total=len(test_data)):\n",
     "\n",
-    "        input_text = format_input(entry)\n",
-    "        tokenizer=tokenizer\n",
+    "    input_text = format_input(entry)\n",
+    "    tokenizer=tokenizer\n",
     "\n",
-    "        token_ids = generate(\n",
-    "            model=model,\n",
-    "            idx=text_to_token_ids(input_text, tokenizer).to(device),\n",
-    "            max_new_tokens=256,\n",
-    "            context_size=BASE_CONFIG[\"context_length\"],\n",
-    "            eos_id=50256\n",
-    "        )\n",
-    "        generated_text = token_ids_to_text(token_ids, tokenizer)\n",
+    "    token_ids = generate(\n",
+    "        model=model,\n",
+    "        idx=text_to_token_ids(input_text, tokenizer).to(device),\n",
+    "        max_new_tokens=256,\n",
+    "        context_size=BASE_CONFIG[\"context_length\"],\n",
+    "        eos_id=50256\n",
+    "    )\n",
+    "    generated_text = token_ids_to_text(token_ids, tokenizer)\n",
     "\n",
-    "        # New: Adjust ###Response -> <|assistant|>\n",
-    "        response_text = generated_text[len(input_text):].replace(\"<|assistant|>:\", \"\").strip()\n",
+    "    # New: Adjust ###Response -> <|assistant|>\n",
+    "    response_text = generated_text[len(input_text):].replace(\"<|assistant|>:\", \"\").strip()\n",
     "\n",
-    "        test_data[i][\"model_response\"] = response_text\n",
+    "    test_data[i][\"model_response\"] = response_text\n",
     "```"
    ]
   },
@@ -229,7 +229,7 @@
    "id": "dd8158e9-cc70-4e0f-88b0-73c3e1d8c030",
    "metadata": {},
    "source": [
-    "```python\n",
+    "```bash\n",
     "python exercise_experiments.py --exercise_solution phi3_prompt\n",
     "```\n",
     "\n",
@@ -273,7 +273,7 @@
     "\n",
     "Let's take a look at some of the responses to make sure they have been formatted correctly:\n",
     "\n",
-    "```\n",
+    "```json\n",
     "    {\n",
     "        \"instruction\": \"Rewrite the sentence using a simile.\",\n",
     "        \"input\": \"The car is very fast.\",\n",
@@ -296,7 +296,7 @@
     "\n",
     "We can evaluate the performance using the Ollama Llama 3 method, which is for your convenience, also implemented in the `python exercise_experiments.py` script, which we can run as follows:\n",
     "\n",
-    "```python\n",
+    "```bash\n",
     "python ollama_evaluate.py --file_path instruction-data-with-response-phi3-prompt.json\n",
     "```\n",
     "\n",
@@ -309,7 +309,7 @@
     "Average score: 48.87\n",
     "```\n",
     "\n",
-    "The score is close to 50, which is in the same ballpark as the score we previously achieved with the Alpaca-style prompts.\n"
+    "The score is close to 50, which is in the same ballpark as the score we previously achieved with the Alpaca-style prompts."
    ]
   },
   {
@@ -802,7 +802,7 @@
    "id": "be9ab66f-5819-4b01-9a03-c45aa3b7c5b8",
    "metadata": {},
    "source": [
-    "```\n",
+    "```json\n",
     "[\n",
     "    {\n",
     "        \"instruction\": \"Edit the following sentence to increase readability: \\\"He made a huge effort and was so successful.\\\"\",\n",
@@ -832,7 +832,7 @@
    "source": [
     "Finally, we can evaluate the finetuned LLM using the [ollama_evaluate.py](ollama_evaluate.py) utility function:\n",
     "\n",
-    "```\n",
+    "```bash\n",
     "python ollama_evaluate.py --file_path instruction-data-with-response-alpaca52k.json\n",
     "```\n",
     "\n",
@@ -867,7 +867,7 @@
     "To instruction finetune the model using LoRA, use the relevant classes and functions from appendix E:\n",
     "\n",
     "```python\n",
-    "    from appendix_E import LoRALayer, LinearWithLoRA, replace_linear_with_lora\n",
+    "from appendix_E import LoRALayer, LinearWithLoRA, replace_linear_with_lora\n",
     "```"
    ]
   },
@@ -961,7 +961,7 @@
     "\n",
     "We can evaluate the performance using the Ollama Llama 3 method, which is for your convenience, also implemented in the `python exercise_experiments.py` script, which we can run as follows:\n",
     "\n",
-    "```python\n",
+    "```bash\n",
     "python ollama_evaluate.py --file_path instruction-data-with-response-lora.json\n",
     "```\n",
     "\n",
@@ -994,7 +994,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.10.11"
   }
  },
  "nbformat": 4,

ch07/01_main-chapter-code/load-finetuned-model.ipynb

@@ -86,8 +86,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from gpt_download import download_and_load_gpt2\n",
-    "from previous_chapters import GPTModel, load_weights_into_gpt\n",
+    "from previous_chapters import GPTModel\n",
     "\n",
     "\n",
     "BASE_CONFIG = {\n",