github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-26 16:43:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix RAG with quantized embeddings notebook (#24422)

Browse Source 
1. Fix HuggingfacePipeline import error to newer partner package
 2. Switch to IPEXModelForCausalLM for performance

There are no dependency changes since optimum intel is also needed for
QuantizedBiEncoderEmbeddings

---------

Co-authored-by: ccurme <chester.curme@gmail.com>
This commit is contained in:
rbrugaro 2024-07-22 06:44:03 -07:00 committed by GitHub
parent 40c02cedaf
commit 37b89fb7fc
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
cookbook/rag_with_quantized_embeddings.ipynb
View File

@ -370,13 +370,14 @@
],
"source": [
"import torch\n",
"from langchain.llms.huggingface_pipeline import HuggingFacePipeline\n",
"from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline\n",
"from langchain_huggingface.llms import HuggingFacePipeline\n",
"from optimum.intel.ipex import IPEXModelForCausalLM\n",
"from transformers import AutoTokenizer, pipeline\n",
"\n",
"model_id = \"Intel/neural-chat-7b-v3-3\"\n",
"tokenizer = AutoTokenizer.from_pretrained(model_id)\n",
"model = AutoModelForCausalLM.from_pretrained(\n",
" model_id, device_map=\"auto\", torch_dtype=torch.bfloat16\n",
"model = IPEXModelForCausalLM.from_pretrained(\n",
" model_id, torch_dtype=torch.bfloat16, export=True\n",
")\n",
"\n",
"pipe = pipeline(\"text-generation\", model=model, tokenizer=tokenizer, max_new_tokens=100)\n",
@ -581,7 +582,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.18"
"version": "3.10.14"
}
},
"nbformat": 4,