Skip to content

Commit

Permalink
feat: fix pre-commit failures
Browse files Browse the repository at this point in the history
  • Loading branch information
tdejager committed Jul 2, 2024
1 parent a8f1a60 commit 33bed3d
Show file tree
Hide file tree
Showing 2 changed files with 2 additions and 3 deletions.
4 changes: 2 additions & 2 deletions examples/llama-index-inference/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -19,8 +19,8 @@ llama_print_timings: eval time = 17786.87 ms / 246 runs ( 72.30 m
llama_print_timings: total time = 19959.11 ms / 317 tokens
```

Opportunities for improvement:
Opportunities for improvement:

- Modify for Linux / CUDA environments to demonstrate a more practical production stack.
- Enhance the pipeline with a RAG workflow, which is what Llama Index is good at.
- Enhance the pipeline with a RAG workflow, which is what Llama Index is good at.
- Experiment with different GGUF models for a quality / performance balance that fits your hardware.
1 change: 0 additions & 1 deletion examples/llama-index-inference/inference.py
Original file line number Diff line number Diff line change
@@ -1,4 +1,3 @@
from llama_index.core import SimpleDirectoryReader, VectorStoreIndex, set_global_tokenizer
from llama_index.llms.llama_cpp import LlamaCPP
from llama_index.llms.llama_cpp.llama_utils import (
messages_to_prompt,
Expand Down

0 comments on commit 33bed3d

Please sign in to comment.