langchain/docs/extras/integrations/llms/mosaicml.ipynb
2023-09-16 17:22:48 -07:00

106 lines
2.4 KiB
Plaintext

{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# MosaicML\n",
"\n",
"[MosaicML](https://docs.mosaicml.com/en/latest/inference.html) offers a managed inference service. You can either use a variety of open source models, or deploy your own.\n",
"\n",
"This example goes over how to use LangChain to interact with MosaicML Inference for text completion."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# sign up for an account: https://forms.mosaicml.com/demo?utm_source=langchain\n",
"\n",
"from getpass import getpass\n",
"\n",
"MOSAICML_API_TOKEN = getpass()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"os.environ[\"MOSAICML_API_TOKEN\"] = MOSAICML_API_TOKEN"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from langchain.llms import MosaicML\n",
"from langchain.prompts import PromptTemplate\nfrom langchain.chains import LLMChain"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"template = \"\"\"Question: {question}\"\"\"\n",
"\n",
"prompt = PromptTemplate(template=template, input_variables=[\"question\"])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"llm = MosaicML(inject_instruction_format=True, model_kwargs={\"max_new_tokens\": 128})"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"llm_chain = LLMChain(prompt=prompt, llm=llm)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"question = \"What is one good reason why you should train a large language model on domain specific data?\"\n",
"\n",
"llm_chain.run(question)"
]
}
],
"metadata": {
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}