Skip to content
This repository has been archived by the owner on Oct 25, 2024. It is now read-only.

Fix missing documentation in LLM runtime, and a broken link + some typos #1128

Merged
merged 3 commits into from
Jan 11, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion intel_extension_for_transformers/llm/runtime/graph/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -408,10 +408,11 @@ while True:
outputs = model.generate(inputs, streamer=streamer, interactive=True, ignore_prompt=True, do_sample=True)
```

## How to use: Python script
## How to use: Straightforward Python script
Install from binary
```shell
pip install intel-extension-for-transformers
pip install -r requirements.txt # under graph folder
```

Build from source
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -167,7 +167,7 @@ def main(args_in: Optional[List[str]] = None) -> None:
convert_cmd.extend(["--outfile", Path(work_path, "ne_{}_f32.bin".format(model_type))])
convert_cmd.extend(["--outtype", "f32"])
convert_cmd.append(args.model)
print("convert model ...")
print("Convert model ...")
subprocess.run(convert_cmd)

# 2. quantize
Expand All @@ -185,7 +185,7 @@ def main(args_in: Optional[List[str]] = None) -> None:
if args.use_ggml:
quant_cmd.extend(["--use_ggml"])
quant_cmd.extend(["--build_dir", args.build_dir])
print("quantize model ...")
print("Quantize model ...")
subprocess.run(quant_cmd)

# 3. inference
Expand All @@ -204,7 +204,7 @@ def main(args_in: Optional[List[str]] = None) -> None:
infer_cmd.extend(["--build_dir", args.build_dir])
if args.shift_roped_k:
infer_cmd.extend(["--shift-roped-k"])
print("inferce model ...")
print("Inference model ...")
subprocess.run(infer_cmd)


Expand Down