very basics

.gitignore

@@ -0,0 +1 @@
+.venv

README

@@ -1 +1,15 @@
-#### checking git capabilities of hugging face
+# Setup
+This is for the gcp vm.  Mine came installed with python3.7 and cuda 11.3
+### Create a venv
+`python3 -m venv .venv`  
+`source .venv/bin/activate`
+You may have to install python3-venv to the machine.
+### Install 
+```
+pip install -r requirements.txt
+pip uninstall -r uninstall.txt
+```
+I had to uninstall some cuda stuff that torch installed to make this work.
+
+
+

llama_test.ipynb

@@ -0,0 +1,93 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import torch\n",
+    "torch.cuda.is_available()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "The tokenizer class you load from this checkpoint is not the same type as the class this function is called from. It may result in unexpected tokenization. \n",
+      "The tokenizer class you load from this checkpoint is 'LLaMATokenizer'. \n",
+      "The class this function is called from is 'LlamaTokenizer'.\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "b687cc7da1a74a058775e5db887f0634",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Loading checkpoint shards:   0%|          | 0/33 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from transformers import LlamaTokenizer, LlamaForCausalLM\n",
+    "tokenizer = LlamaTokenizer.from_pretrained(\"decapoda-research/llama-7b-hf\", add_eos_token=True)\n",
+    "\n",
+    "model = LlamaForCausalLM.from_pretrained(\n",
+    "    \"decapoda-research/llama-7b-hf\",\n",
+    "    load_in_8bit=True,\n",
+    "    device_map=\"auto\",\n",
+    "    torch_dtype=torch.float16\n",
+    ")\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "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": "3.7.3"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "6a381460736e8a0eabfb35eafae436ba15c06439de44e28b965ea473bd8dda90"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

requirements.txt

@@ -0,0 +1,8 @@
+numpy
+ipykernel
+ipywidgets
+torch
+sentencepiece
+transformers
+accelerate
+bitsandbytes

uninstall.txt

@@ -0,0 +1 @@
+nvidia_cublas_cu11