brad/LLM_Engineering_OLD
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Updated README and Week 8 coming together

Browse Source
This commit is contained in:
Edward Donner
2024-09-26 10:04:55 -04:00
parent 0fd4c84b24
commit 2f997952fc
17 changed files with 3204 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

294
week8_wip/day1.ipynb Normal file
View File

@@ -0,0 +1,294 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "56297249-4a8c-4e67-b8c3-a0d8652c104e",
"metadata": {},
"outputs": [],
"source": [
"import modal"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "0d240622-8422-4c99-8464-c04d063e4cb6",
"metadata": {},
"outputs": [],
"source": [
"# !modal setup"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "3b133701-f550-44a1-a67f-eb7ccc4769a9",
"metadata": {},
"outputs": [],
"source": [
"from hello import app, hello"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "0f3f73ae-1295-49f3-9099-b8b41fc3429b",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Hello from Seaport, New York, US!!'"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"with app.run(show_progress=False):\n",
" reply=hello.local()\n",
"reply"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "c1d8c6f9-edc7-4e52-9b3a-c07d7cff1ac7",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Hello from Frankfurt am Main, Hesse, DE!!'"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"with app.run(show_progress=False):\n",
" reply=hello.remote()\n",
"reply"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "cb8b6c41-8259-4329-b1c4-a1f67d26d1be",
"metadata": {},
"outputs": [],
"source": [
"import modal\n",
"from llama import app, generate"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "db4a718a-d95d-4f61-9688-c9df21d88fe6",
"metadata": {},
"outputs": [],
"source": [
"with modal.enable_output():\n",
" with app.run():\n",
" result=generate.remote(\"Life is a mystery, everyone must stand alone, I hear\")\n",
"result"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9a9a6844-29ec-4264-8e72-362d976b3968",
"metadata": {},
"outputs": [],
"source": [
"import modal\n",
"from pricer_ephemeral import app, price"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "50e6cf99-8959-4ae3-ba02-e325cb7fff94",
"metadata": {},
"outputs": [],
"source": [
"with modal.enable_output():\n",
" with app.run():\n",
" result=price.remote(\"Quadcast HyperX condenser mic, connects via usb-c to your computer for crystal clear audio\")\n",
"result"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7f90d857-2f12-4521-bb90-28efd917f7d1",
"metadata": {},
"outputs": [],
"source": [
"!modal deploy pricer_service"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1dec70ff-1986-4405-8624-9bbbe0ce1f4a",
"metadata": {},
"outputs": [],
"source": [
"pricer = modal.Function.lookup(\"pricer-service\", \"price\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "17776139-0d9e-4ad0-bcd0-82d3a92ca61f",
"metadata": {},
"outputs": [],
"source": [
"pricer.remote(\"Quadcast HyperX condenser mic, connects via usb-c to your computer for crystal clear audio\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "58f5d19f-8ffc-496c-832b-04e0d5892f54",
"metadata": {},
"outputs": [],
"source": [
"import modal"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "f56d1e55-2a03-4ce2-bb47-2ab6b9175a02",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[2K\u001b[34m⠸\u001b[0m Creating objects.....\n",
"\u001b[38;5;244m└── \u001b[0m\u001b[34m⠋\u001b[0m Creating mount /Users/ed/dev/llm_engineering/week8/pricer_service2.py: \n",
"\u001b[2K\u001b[1A\u001b[2K\u001b[1A\u001b[2K\u001b[34m⠦\u001b[0m Creating objects...\n",
"\u001b[38;5;244m└── \u001b[0m\u001b[34m⠸\u001b[0m Creating mount /Users/ed/dev/llm_engineering/week8/pricer_service2.py: \n",
"\u001b[2K\u001b[1A\u001b[2K\u001b[1A\u001b[2K\u001b[34m⠏\u001b[0m Creating objects...\n",
"\u001b[38;5;244m└── \u001b[0m\u001b[34m⠦\u001b[0m Creating mount /Users/ed/dev/llm_engineering/week8/pricer_service2.py: \n",
"\u001b[2K\u001b[1A\u001b[2K\u001b[1A\u001b[2K\u001b[34m⠹\u001b[0m Creating objects...\n",
"\u001b[38;5;244m├── \u001b[0m🔨 Created mount /Users/ed/dev/llm_engineering/week8/pricer_service2.py\n",
"\u001b[2K\u001b[1A\u001b[2K\u001b[1A\u001b[2K\u001b[34m⠴\u001b[0m Creating objects...load_model_to_folder.\n",
"\u001b[38;5;244m├── \u001b[0m🔨 Created mount /Users/ed/dev/llm_engineering/week8/pricer_service2.py\n",
"\u001b[38;5;244m├── \u001b[0m🔨 Created function Pricer.download_model_to_folder.\n",
"\u001b[38;5;244m├── \u001b[0m🔨 Created function Pricer.*.\n",
"\u001b[2K\u001b[1A\u001b[2K\u001b[1A\u001b[2K\u001b[1A\u001b[2K\u001b[1A\u001b[2K\u001b[34m⠴\u001b[0m Creating objects...\n",
"\u001b[38;5;244m├── \u001b[0m🔨 Created mount /Users/ed/dev/llm_engineering/week8/pricer_service2.py\n",
"\u001b[38;5;244m├── \u001b[0m🔨 Created function Pricer.download_model_to_folder.\n",
"\u001b[38;5;244m├── \u001b[0m🔨 Created function Pricer.*.\n",
"\u001b[38;5;244m└── \u001b[0m🔨 Created function Pricer.price.\n",
"\u001b[1A\u001b[2K\u001b[1A\u001b[2K\u001b[1A\u001b[2K\u001b[1A\u001b[2K\u001b[1A\u001b[2K\u001b[32m✓\u001b[0m Created objects.\n",
"\u001b[38;5;244m├── \u001b[0m🔨 Created mount /Users/ed/dev/llm_engineering/week8/pricer_service2.py\n",
"\u001b[38;5;244m├── \u001b[0m🔨 Created function Pricer.download_model_to_folder.\n",
"\u001b[38;5;244m├── \u001b[0m🔨 Created function Pricer.*.\n",
"\u001b[38;5;244m└── \u001b[0m🔨 Created function Pricer.price.\n",
"\u001b[32m✓\u001b[0m App deployed in 1.570s! 🎉\n",
"\n",
"View Deployment: \u001b[35mhttps://modal.com/apps/ed-donner/main/deployed/pricer-service\u001b[0m\n"
]
}
],
"source": [
"!modal deploy pricer_service2"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "9e19daeb-1281-484b-9d2f-95cc6fed2622",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"133.0\n"
]
}
],
"source": [
"\n",
"import modal\n",
"\n",
"Pricer = modal.Cls.lookup(\"pricer-service\", \"Pricer\")\n",
"pricer = Pricer()\n",
"reply = pricer.price.remote(\"Quadcast HyperX condenser mic, connects via usb-c to your computer for crystal clear audio\")\n",
"print(reply)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "ac331454-21e2-4b37-9602-4667006e34ee",
"metadata": {},
"outputs": [],
"source": [
"reply = pricer.price.remote(\"iphone SE\")\n"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "c3a71dcd-b71d-4c48-b0d9-3ac296d2046a",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"299.0"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"reply"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ba9aedca-6a7b-4d30-9f64-59d76f76fb6d",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.10"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

328
week8_wip/day2.0.ipynb Normal file
View File

@@ -0,0 +1,328 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "993a2a24-1a58-42be-8034-6d116fb8d786",
"metadata": {},
"outputs": [],
"source": [
"# imports\n",
"\n",
"import os\n",
"import re\n",
"import math\n",
"import json\n",
"from tqdm import tqdm\n",
"import random\n",
"from dotenv import load_dotenv\n",
"from huggingface_hub import login\n",
"import numpy as np\n",
"import pickle\n",
"from sentence_transformers import SentenceTransformer\n",
"from datasets import load_dataset\n",
"import chromadb\n",
"from items import Item\n",
"from sklearn.manifold import TSNE\n",
"import plotly.graph_objects as go"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "0e31676f-6f31-465f-a80e-02d51ff8425a",
"metadata": {},
"outputs": [],
"source": [
"# CONSTANTS\n",
"\n",
"HF_USER = \"ed-donner\" # your HF name here! Or use mine if you just want to reproduce my results.\n",
"DATASET_NAME = f\"{HF_USER}/pricer-data\"\n",
"QUESTION = \"How much does this cost to the nearest dollar?\\n\\n\"\n",
"DB = \"products_vectorstore\""
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "2359ccc0-dbf2-4b1e-9473-e472b32f548b",
"metadata": {},
"outputs": [],
"source": [
"# environment\n",
"\n",
"load_dotenv()\n",
"os.environ['OPENAI_API_KEY'] = os.getenv('OPENAI_API_KEY', 'your-key-if-not-using-env')\n",
"os.environ['HF_TOKEN'] = os.getenv('HF_TOKEN', 'your-key-if-not-using-env')"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "a29fcc4e-e4d7-4c54-aa6b-e5d1111ea9c4",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Token is valid (permission: write).\n",
"Your token has been saved in your configured git credential helpers (osxkeychain).\n",
"Your token has been saved to /Users/ed/.cache/huggingface/token\n",
"Login successful\n"
]
}
],
"source": [
"# Log in to HuggingFace\n",
"\n",
"hf_token = os.environ['HF_TOKEN']\n",
"login(hf_token, add_to_git_credential=True)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "688bd995-ec3e-43cd-8179-7fe14b275877",
"metadata": {},
"outputs": [],
"source": [
"# Let's avoid curating all our data again! Load in the pickle files:\n",
"\n",
"with open('train.pkl', 'rb') as file:\n",
" train = pickle.load(file)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "2817eaf5-4302-4a18-9148-d1062e3b3dbb",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"400000"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"items = train\n",
"len(items)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "f4aab95e-d719-4476-b6e7-e248120df25a",
"metadata": {},
"outputs": [],
"source": [
"client = chromadb.PersistentClient(path=DB)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "5f95dafd-ab80-464e-ba8a-dec7a2424780",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Deleted existing collection: products\n"
]
}
],
"source": [
"# Check if the collection exists and delete it if it does\n",
"collection_name = \"products\"\n",
"existing_collection_names = [collection.name for collection in client.list_collections()]\n",
"if collection_name in existing_collection_names:\n",
" client.delete_collection(collection_name)\n",
" print(f\"Deleted existing collection: {collection_name}\")\n",
"\n",
"collection = client.create_collection(collection_name)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "a87db200-d19d-44bf-acbd-15c45c70f5c9",
"metadata": {},
"outputs": [],
"source": [
"model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "38de1bf8-c9b5-45b4-9f4b-86af93b3f80d",
"metadata": {},
"outputs": [],
"source": [
"def description(item):\n",
" text = item.prompt.replace(\"How much does this cost to the nearest dollar?\\n\\n\", \"\")\n",
" return text.split(\"\\n\\nPrice is $\")[0]"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "8c79e2fe-1f50-4ebf-9a93-34f3088f2996",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████| 400/400 [21:47<00:00, 3.27s/it]\n"
]
}
],
"source": [
"for i in tqdm(range(0, len(items), 1000)):\n",
" documents = [description(item) for item in items[i: i+1000]]\n",
" vectors = model.encode(documents).astype(float).tolist()\n",
" metadatas = [{\"category\": item.category, \"price\": item.price} for item in items[i: i+1000]]\n",
" ids = [f\"doc_{j}\" for j in range(i, i+1000)]\n",
" collection.add(\n",
" ids=ids,\n",
" documents=documents,\n",
" embeddings=vectors,\n",
" metadatas=metadatas\n",
" )"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "525fc313-8a16-4ac0-8c42-6a6d1ba1c9b8",
"metadata": {},
"outputs": [],
"source": [
"CATEGORIES = ['Appliances', 'Automotive', 'Cell_Phones_and_Accessories', 'Electronics','Musical_Instruments', 'Office_Products', 'Tools_and_Home_Improvement', 'Toys_and_Games']\n",
"COLORS = ['red', 'blue', 'brown', 'orange', 'yellow', 'green' , 'purple', 'cyan']"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a4cf1c9a-1ced-48d4-974c-3c850905034e",
"metadata": {},
"outputs": [],
"source": [
"# Prework\n",
"\n",
"vectors_np = np.array(vectors)\n",
"colors = [COLORS[CATEGORIES.index(t)] for t in categories]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0c6718b3-e0fd-4319-a1b5-d9d34d6b1dd9",
"metadata": {},
"outputs": [],
"source": [
"# We humans find it easier to visalize things in 2D!\n",
"# Reduce the dimensionality of the vectors to 2D using t-SNE\n",
"# (t-distributed stochastic neighbor embedding)\n",
"\n",
"tsne = TSNE(n_components=2, random_state=42)\n",
"reduced_vectors = tsne.fit_transform(vectors_np)\n",
"\n",
"# Create the 2D scatter plot\n",
"fig = go.Figure(data=[go.Scatter(\n",
" x=reduced_vectors[:, 0],\n",
" y=reduced_vectors[:, 1],\n",
" mode='markers',\n",
" marker=dict(size=3, color=colors, opacity=0.8),\n",
" text=[f\"Category: {c}<br>Text: {d[:100]}...\" for c, d in zip(categories, descriptions)],\n",
" hoverinfo='text'\n",
")])\n",
"\n",
"fig.update_layout(\n",
" title='2D Chroma Vector Store Visualization',\n",
" scene=dict(xaxis_title='x',yaxis_title='y'),\n",
" width=1200,\n",
" height=800,\n",
" margin=dict(r=20, b=10, l=10, t=40)\n",
")\n",
"\n",
"fig.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c54df150-c8d8-4bc3-8877-6759691eeb42",
"metadata": {},
"outputs": [],
"source": [
"# Let's try 3D!\n",
"\n",
"tsne = TSNE(n_components=3, random_state=42)\n",
"reduced_vectors = tsne.fit_transform(vectors_np)\n",
"\n",
"# Create the 3D scatter plot\n",
"fig = go.Figure(data=[go.Scatter3d(\n",
" x=reduced_vectors[:, 0],\n",
" y=reduced_vectors[:, 1],\n",
" z=reduced_vectors[:, 2],\n",
" mode='markers',\n",
" marker=dict(size=3, color=colors, opacity=0.7),\n",
" text=[f\"Category: {c}<br>Text: {d[:100]}...\" for c, d in zip(categories, descriptions)],\n",
" hoverinfo='text'\n",
")])\n",
"\n",
"fig.update_layout(\n",
" title='3D Chroma Vector Store Visualization',\n",
" scene=dict(xaxis_title='x', yaxis_title='y', zaxis_title='z'),\n",
" width=1200,\n",
" height=800,\n",
" margin=dict(r=20, b=10, l=10, t=40)\n",
")\n",
"\n",
"fig.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e8fb2a63-24c5-4dce-9e63-aa208272f82d",
"metadata": {},
"outputs": [],
"source": [
"def "
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.10"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

150
week8_wip/day2.2.ipynb Normal file
View File

@@ -0,0 +1,150 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "993a2a24-1a58-42be-8034-6d116fb8d786",
"metadata": {},
"outputs": [],
"source": [
"# imports\n",
"\n",
"import os\n",
"import re\n",
"import math\n",
"import json\n",
"from tqdm import tqdm\n",
"import random\n",
"from dotenv import load_dotenv\n",
"from huggingface_hub import login\n",
"import numpy as np\n",
"import pickle\n",
"from sentence_transformers import SentenceTransformer\n",
"from datasets import load_dataset\n",
"import chromadb\n",
"from items import Item\n",
"from sklearn.manifold import TSNE\n",
"import plotly.graph_objects as go"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "f4aab95e-d719-4476-b6e7-e248120df25a",
"metadata": {},
"outputs": [],
"source": [
"DB = \"products_vectorstore\"\n",
"client = chromadb.PersistentClient(path=DB)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "5f95dafd-ab80-464e-ba8a-dec7a2424780",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Deleted existing collection: products\n"
]
}
],
"source": [
"collection = client.get_or_create_collection('products')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "525fc313-8a16-4ac0-8c42-6a6d1ba1c9b8",
"metadata": {},
"outputs": [],
"source": [
"CATEGORIES = ['Appliances', 'Automotive', 'Cell_Phones_and_Accessories', 'Electronics','Musical_Instruments', 'Office_Products', 'Tools_and_Home_Improvement', 'Toys_and_Games']\n",
"COLORS = ['red', 'blue', 'brown', 'orange', 'yellow', 'green' , 'purple', 'cyan']"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a4cf1c9a-1ced-48d4-974c-3c850905034e",
"metadata": {},
"outputs": [],
"source": [
"# Prework\n",
"result = collection.get(include=['embeddings', 'documents', 'metadatas'])\n",
"vectors = np.array(result['embeddings'])\n",
"documents = result['documents']\n",
"categories = [metadata['category'] for metadata in result['metadatas']]\n",
"colors = [COLORS[CATEGORIES.index(c)] for c in categories]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c54df150-c8d8-4bc3-8877-6759691eeb42",
"metadata": {},
"outputs": [],
"source": [
"# Let's try 3D!\n",
"\n",
"tsne = TSNE(n_components=3, random_state=42, max_iter=250, n_jobs=-1)\n",
"reduced_vectors = tsne.fit_transform(vectors)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e8fb2a63-24c5-4dce-9e63-aa208272f82d",
"metadata": {},
"outputs": [],
"source": [
"\n",
"# Create the 3D scatter plot\n",
"fig = go.Figure(data=[go.Scatter3d(\n",
" x=reduced_vectors[:, 0],\n",
" y=reduced_vectors[:, 1],\n",
" z=reduced_vectors[:, 2],\n",
" mode='markers',\n",
" marker=dict(size=3, color=colors, opacity=0.7),\n",
" text=[f\"Category: {c}<br>Text: {d[:100]}...\" for c, d in zip(categories, documents)],\n",
" hoverinfo='text'\n",
")])\n",
"\n",
"fig.update_layout(\n",
" title='3D Chroma Vector Store Visualization',\n",
" scene=dict(xaxis_title='x', yaxis_title='y', zaxis_title='z'),\n",
" width=1200,\n",
" height=800,\n",
" margin=dict(r=20, b=10, l=10, t=40)\n",
")\n",
"\n",
"fig.show()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.10"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

618
week8_wip/day2.3.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

1257
week8_wip/day2.4.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

19
week8_wip/hello.py Normal file
View File

@@ -0,0 +1,19 @@
import modal
from modal import App, Volume, Image
# Setup
app = modal.App("hello")
image = Image.debian_slim().pip_install("requests")
gpu = "T4"
# Hello!
@app.function(image=image)
def hello() -> str:
import requests
response = requests.get('https://ipinfo.io/json')
data = response.json()
city, region, country = data['city'], data['region'], data['country']
return f"Hello from {city}, {region}, {country}!!"

101
week8_wip/items.py Normal file
View File

@@ -0,0 +1,101 @@
from typing import Optional
from transformers import AutoTokenizer
import re
BASE_MODEL = "meta-llama/Meta-Llama-3.1-8B"
MIN_TOKENS = 150
MAX_TOKENS = 160
MIN_CHARS = 300
CEILING_CHARS = MAX_TOKENS * 7
class Item:
"""
An Item is a cleaned, curated datapoint of a Product with a Price
"""
tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL, trust_remote_code=True)
PREFIX = "Price is $"
QUESTION = "How much does this cost to the nearest dollar?"
REMOVALS = ['"Batteries Included?": "No"', '"Batteries Included?": "Yes"', '"Batteries Required?": "No"', '"Batteries Required?": "Yes"', "By Manufacturer", "Item", "Date First", "Package", ":", "Number of", "Best Sellers", "Number", "Product "]
title: str
price: float
category: str
token_count: int = 0
details: Optional[str]
prompt: Optional[str] = None
include = False
def __init__(self, data, price):
self.title = data['title']
self.price = price
self.parse(data)
def scrub_details(self):
"""
Clean up the details string by removing common text that doesn't add value
"""
details = self.details
for remove in self.REMOVALS:
details = details.replace(remove, "")
return details
def scrub(self, stuff):
"""
Clean up the provided text by removing unnecessary characters and whitespace
Also remove words that are 7+ chars and contain numbers, as these are likely irrelevant product numbers
"""
stuff = re.sub(r'[:\[\]"{}【】\s]+', ' ', stuff).strip()
stuff = stuff.replace(" ,", ",").replace(",,,",",").replace(",,",",")
words = stuff.split(' ')
select = [word for word in words if len(word)<7 or not any(char.isdigit() for char in word)]
return " ".join(select)
def parse(self, data):
"""
Parse this datapoint and if it fits within the allowed Token range,
then set include to True
"""
contents = '\n'.join(data['description'])
if contents:
contents += '\n'
features = '\n'.join(data['features'])
if features:
contents += features + '\n'
self.details = data['details']
if self.details:
contents += self.scrub_details() + '\n'
if len(contents) > MIN_CHARS:
contents = contents[:CEILING_CHARS]
text = f"{self.scrub(self.title)}\n{self.scrub(contents)}"
tokens = self.tokenizer.encode(text, add_special_tokens=False)
if len(tokens) > MIN_TOKENS:
tokens = tokens[:MAX_TOKENS]
text = self.tokenizer.decode(tokens)
self.make_prompt(text)
self.include = True
def make_prompt(self, text):
"""
Set the prompt instance variable to be a prompt appropriate for training
"""
self.prompt = f"{self.QUESTION}\n\n{text}\n\n"
self.prompt += f"{self.PREFIX}{str(round(self.price))}.00"
self.token_count = len(self.tokenizer.encode(self.prompt, add_special_tokens=False))
def test_prompt(self):
"""
Return a prompt suitable for testing, with the actual price removed
"""
return self.prompt.split(self.PREFIX)[0] + self.PREFIX
def __repr__(self):
"""
Return a String version of this Item
"""
return f"<{self.title} = ${self.price}>"

44
week8_wip/llama.py Normal file
View File

@@ -0,0 +1,44 @@
import modal
from modal import App, Volume, Image
# Setup
app = modal.App("llama")
image = Image.debian_slim().pip_install("torch", "transformers", "bitsandbytes", "accelerate")
secrets = [modal.Secret.from_name("hf-secret")]
GPU = "T4"
MODEL_NAME = "meta-llama/Meta-Llama-3.1-8B"
@app.function(image=image, secrets=secrets, gpu=GPU)
def generate(prompt: str) -> str:
import os
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, set_seed
# Quant Config
quant_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_use_double_quant=True,
bnb_4bit_compute_dtype=torch.bfloat16,
bnb_4bit_quant_type="nf4"
)
# Load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
tokenizer.pad_token = tokenizer.eos_token
tokenizer.padding_side = "right"
model = AutoModelForCausalLM.from_pretrained(
MODEL_NAME,
quantization_config=quant_config,
device_map="auto"
)
set_seed(42)
inputs = tokenizer.encode(prompt, return_tensors="pt").to("cuda")
attention_mask = torch.ones(inputs.shape, device="cuda")
outputs = model.generate(inputs, attention_mask=attention_mask, max_new_tokens=5, num_return_sequences=1)
return tokenizer.decode(outputs[0])

66
week8_wip/pricer_ephemeral.py Normal file
View File

@@ -0,0 +1,66 @@
import modal
from modal import App, Volume, Image
# Setup
app = modal.App("pricer")
image = Image.debian_slim().pip_install("torch", "transformers", "bitsandbytes", "accelerate", "peft")
secrets = [modal.Secret.from_name("hf-secret")]
# Constants
GPU = "T4"
BASE_MODEL = "meta-llama/Meta-Llama-3.1-8B"
PROJECT_NAME = "pricer"
HF_USER = "ed-donner" # your HF name here! Or use mine if you just want to reproduce my results.
RUN_NAME = "2024-09-13_13.04.39"
PROJECT_RUN_NAME = f"{PROJECT_NAME}-{RUN_NAME}"
REVISION = "e8d637df551603dc86cd7a1598a8f44af4d7ae36"
FINETUNED_MODEL = f"{HF_USER}/{PROJECT_RUN_NAME}"
@app.function(image=image, secrets=secrets, gpu=GPU)
def price(description: str) -> float:
import os
import re
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, set_seed
from peft import PeftModel
QUESTION = "How much does this cost to the nearest dollar?"
PREFIX = "Price is $"
prompt = f"{QUESTION}\n{description}\n{PREFIX}"
# Quant Config
quant_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_use_double_quant=True,
bnb_4bit_compute_dtype=torch.bfloat16,
bnb_4bit_quant_type="nf4"
)
# Load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL)
tokenizer.pad_token = tokenizer.eos_token
tokenizer.padding_side = "right"
base_model = AutoModelForCausalLM.from_pretrained(
BASE_MODEL,
quantization_config=quant_config,
device_map="auto"
)
fine_tuned_model = PeftModel.from_pretrained(base_model, FINETUNED_MODEL, revision=REVISION)
set_seed(42)
inputs = tokenizer.encode(prompt, return_tensors="pt").to("cuda")
attention_mask = torch.ones(inputs.shape, device="cuda")
outputs = fine_tuned_model.generate(inputs, attention_mask=attention_mask, max_new_tokens=5, num_return_sequences=1)
result = tokenizer.decode(outputs[0])
contents = result.split("Price is $")[1]
contents = contents.replace(',','')
match = re.search(r"[-+]?\d*\.\d+|\d+", contents)
return float(match.group()) if match else 0

66
week8_wip/pricer_service.py Normal file
View File

@@ -0,0 +1,66 @@
import modal
from modal import App, Volume, Image
# Setup - define our infrastructure with code!
app = modal.App("pricer-service")
image = Image.debian_slim().pip_install("torch", "transformers", "bitsandbytes", "accelerate", "peft")
secrets = [modal.Secret.from_name("hf-secret")]
# Constants
GPU = "T4"
BASE_MODEL = "meta-llama/Meta-Llama-3.1-8B"
PROJECT_NAME = "pricer"
HF_USER = "ed-donner" # your HF name here! Or use mine if you just want to reproduce my results.
RUN_NAME = "2024-09-13_13.04.39"
PROJECT_RUN_NAME = f"{PROJECT_NAME}-{RUN_NAME}"
REVISION = "e8d637df551603dc86cd7a1598a8f44af4d7ae36"
FINETUNED_MODEL = f"{HF_USER}/{PROJECT_RUN_NAME}"
@app.function(image=image, secrets=secrets, gpu=GPU)
def price(description: str) -> float:
import os
import re
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, set_seed
from peft import PeftModel
QUESTION = "How much does this cost to the nearest dollar?"
PREFIX = "Price is $"
prompt = f"{QUESTION}\n{description}\n{PREFIX}"
# Quant Config
quant_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_use_double_quant=True,
bnb_4bit_compute_dtype=torch.bfloat16,
bnb_4bit_quant_type="nf4"
)
# Load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL)
tokenizer.pad_token = tokenizer.eos_token
tokenizer.padding_side = "right"
base_model = AutoModelForCausalLM.from_pretrained(
BASE_MODEL,
quantization_config=quant_config,
device_map="auto"
)
fine_tuned_model = PeftModel.from_pretrained(base_model, FINETUNED_MODEL, revision=REVISION)
set_seed(42)
inputs = tokenizer.encode(prompt, return_tensors="pt").to("cuda")
attention_mask = torch.ones(inputs.shape, device="cuda")
outputs = fine_tuned_model.generate(inputs, attention_mask=attention_mask, max_new_tokens=5, num_return_sequences=1)
result = tokenizer.decode(outputs[0])
contents = result.split("Price is $")[1]
contents = contents.replace(',','')
match = re.search(r"[-+]?\d*\.\d+|\d+", contents)
return float(match.group()) if match else 0

84
week8_wip/pricer_service2.py Normal file
View File

@@ -0,0 +1,84 @@
import modal
from modal import App, Volume, Image
# Setup - define our infrastructure with code!
app = modal.App("pricer-service")
image = Image.debian_slim().pip_install("huggingface", "torch", "transformers", "bitsandbytes", "accelerate", "peft")
secrets = [modal.Secret.from_name("hf-secret")]
# Constants
GPU = "T4"
BASE_MODEL = "meta-llama/Meta-Llama-3.1-8B"
PROJECT_NAME = "pricer"
HF_USER = "ed-donner" # your HF name here! Or use mine if you just want to reproduce my results.
RUN_NAME = "2024-09-13_13.04.39"
PROJECT_RUN_NAME = f"{PROJECT_NAME}-{RUN_NAME}"
REVISION = "e8d637df551603dc86cd7a1598a8f44af4d7ae36"
FINETUNED_MODEL = f"{HF_USER}/{PROJECT_RUN_NAME}"
QUESTION = "How much does this cost to the nearest dollar?"
PREFIX = "Price is $"
@app.cls(image=image, secrets=secrets, gpu=GPU)
class Pricer:
@modal.build()
def download_model_to_folder(self):
from huggingface_hub import snapshot_download
import os
MODEL_DIR = "~/.cache/huggingface/hub/"
os.makedirs(MODEL_DIR, exist_ok=True)
snapshot_download(BASE_MODEL, local_dir=MODEL_DIR)
snapshot_download(FINETUNED_MODEL, revision=REVISION, local_dir=MODEL_DIR)
@modal.enter()
def setup(self):
import os
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, set_seed
from peft import PeftModel
# Quant Config
quant_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_use_double_quant=True,
bnb_4bit_compute_dtype=torch.bfloat16,
bnb_4bit_quant_type="nf4"
)
# Load model and tokenizer
self.tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL)
self.tokenizer.pad_token = self.tokenizer.eos_token
self.tokenizer.padding_side = "right"
self.base_model = AutoModelForCausalLM.from_pretrained(
BASE_MODEL,
quantization_config=quant_config,
device_map="auto"
)
self.fine_tuned_model = PeftModel.from_pretrained(self.base_model, FINETUNED_MODEL, revision=REVISION)
@modal.method()
def price(self, description: str) -> float:
import os
import re
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, set_seed
from peft import PeftModel
set_seed(42)
prompt = f"{QUESTION}\n\n{description}\n\n{PREFIX}"
inputs = self.tokenizer.encode(prompt, return_tensors="pt").to("cuda")
attention_mask = torch.ones(inputs.shape, device="cuda")
outputs = self.fine_tuned_model.generate(inputs, attention_mask=attention_mask, max_new_tokens=5, num_return_sequences=1)
result = self.tokenizer.decode(outputs[0])
contents = result.split("Price is $")[1]
contents = contents.replace(',','')
match = re.search(r"[-+]?\d*\.\d+|\d+", contents)
return float(match.group()) if match else 0

75
week8_wip/testing.py Normal file
View File

@@ -0,0 +1,75 @@
import math
import matplotlib.pyplot as plt
GREEN = "\033[92m"
YELLOW = "\033[93m"
RED = "\033[91m"
RESET = "\033[0m"
COLOR_MAP = {"red":RED, "orange": YELLOW, "green": GREEN}
class Tester:
def __init__(self, predictor, data, title=None, size=250):
self.predictor = predictor
self.data = data
self.title = title or predictor.__name__.replace("_", " ").title()
self.size = size
self.guesses = []
self.truths = []
self.errors = []
self.sles = []
self.colors = []
def color_for(self, error, truth):
if error<40 or error/truth < 0.2:
return "green"
elif error<80 or error/truth < 0.4:
return "orange"
else:
return "red"
def run_datapoint(self, i):
datapoint = self.data[i]
guess = self.predictor(datapoint)
truth = datapoint.price
error = abs(guess - truth)
log_error = math.log(truth+1) - math.log(guess+1)
sle = log_error ** 2
color = self.color_for(error, truth)
title = datapoint.title if len(datapoint.title) <= 40 else datapoint.title[:40]+"..."
self.guesses.append(guess)
self.truths.append(truth)
self.errors.append(error)
self.sles.append(sle)
self.colors.append(color)
print(f"{COLOR_MAP[color]}{i+1}: Guess: ${guess:,.2f} Truth: ${truth:,.2f} Error: ${error:,.2f} SLE: {sle:,.2f} Item: {title}{RESET}")
def chart(self, title):
max_error = max(self.errors)
plt.figure(figsize=(12, 8))
max_val = max(max(self.truths), max(self.guesses))
plt.plot([0, max_val], [0, max_val], color='deepskyblue', lw=2, alpha=0.6)
plt.scatter(self.truths, self.guesses, s=3, c=self.colors)
plt.xlabel('Ground Truth')
plt.ylabel('Model Estimate')
plt.xlim(0, max_val)
plt.ylim(0, max_val)
plt.title(title)
plt.show()
def report(self):
average_error = sum(self.errors) / self.size
rmsle = math.sqrt(sum(self.sles) / self.size)
hits = sum(1 for color in self.colors if color=="green")
title = f"{self.title} Error=${average_error:,.2f} RMSLE={rmsle:,.2f} Hits={hits/self.size*100:.1f}%"
self.chart(title)
def run(self):
self.error = 0
for i in range(self.size):
self.run_datapoint(i)
self.report()
@classmethod
def test(cls, function, data):
cls(function, data).run()