Yi model from 01.ai , example (#13375)

Added an example with new soa `Yi` model to `HuggingFace-hub` notebook
This commit is contained in:
Leonid Ganeline 2023-11-14 17:10:53 -08:00 committed by GitHub
parent 38180ad25f
commit 342ed5c77a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -101,8 +101,8 @@
"metadata": {},
"outputs": [],
"source": [
"from langchain.chains import LLMChain\n",
"from langchain.prompts import PromptTemplate"
"from langchain.prompts import PromptTemplate\n",
"from langchain.chains import LLMChain"
]
},
{
@ -397,10 +397,46 @@
"print(llm_chain.run(question))"
]
},
{
"cell_type": "markdown",
"id": "e3871376-ed0e-49a8-8d9b-7e60dbbd2b35",
"metadata": {},
"source": [
"### `Yi` series models, by `01.ai`\n",
"\n",
">The `Yi` series models are large language models trained from scratch by developers at [01.ai](https://01.ai/). The first public release contains two bilingual(English/Chinese) base models with the parameter sizes of 6B(`Yi-6B`) and 34B(`Yi-34B`). Both of them are trained with 4K sequence length and can be extended to 32K during inference time. The `Yi-6B-200K` and `Yi-34B-200K` are base model with 200K context length.\n",
"\n",
"Here we test the [Yi-34B](https://huggingface.co/01-ai/Yi-34B) model."
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "1c9d3125-3f50-48b8-93b6-b50847207afa",
"metadata": {},
"outputs": [],
"source": [
"repo_id = \"01-ai/Yi-34B\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1dd67c1e-1efc-4def-bde4-2e5265725303",
"id": "8b661069-8229-4850-9f13-c4ca28c0c96b",
"metadata": {},
"outputs": [],
"source": [
"llm = HuggingFaceHub(\n",
" repo_id=repo_id, model_kwargs={\"max_length\": 128, \"temperature\": 0.5}\n",
")\n",
"llm_chain = LLMChain(prompt=prompt, llm=llm)\n",
"print(llm_chain.run(question))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "dd6f3edc-9f97-47a6-ab2c-116756babbe6",
"metadata": {},
"outputs": [],
"source": []