release v0.2.32

Author: merrymercy

README.md

@@ -66,7 +66,7 @@ pip3 install -e ".[model_worker,webui]"
 
 ## Model Weights
 ### Vicuna Weights
-[Vicuna](https://lmsys.org/blog/2023-03-30-vicuna/) is based on LLaMA and should be used under LLaMA's [model license](https://github.com/facebookresearch/llama/blob/main/LICENSE).
+[Vicuna](https://lmsys.org/blog/2023-03-30-vicuna/) is based on Llama 2 and should be used under Llama's [model license](https://github.com/facebookresearch/llama/blob/main/LICENSE).
 
 You can use the commands below to start chatting. It will automatically download the weights from Hugging Face repos.
 See more command options and how to handle out-of-memory in the "Inference with Command Line Interface" section below.
@@ -84,7 +84,7 @@ See more command options and how to handle out-of-memory in the "Inference with
 **Old weights**: see [docs/vicuna_weights_version.md](docs/vicuna_weights_version.md) for all versions of weights and their differences.
 
 ### LongChat
-We release [LongChat](https://lmsys.org/blog/2023-06-29-longchat/) models under LLaMA's [model license](https://github.com/facebookresearch/llama/blob/main/LICENSE).
+We release [LongChat](https://lmsys.org/blog/2023-06-29-longchat/) models under Llama's [model license](https://github.com/facebookresearch/llama/blob/main/LICENSE).
 
 | Size | Chat Command | Hugging Face Repo |
 | ---  | --- | --- |
@@ -276,7 +276,7 @@ MT-bench is the new recommended way to benchmark your models. If you are still l
 ## Fine-tuning
 ### Data
 
-Vicuna is created by fine-tuning a LLaMA base model using approximately 125K user-shared conversations gathered from ShareGPT.com with public APIs. To ensure data quality, we convert the HTML back to markdown and filter out some inappropriate or low-quality samples. Additionally, we divide lengthy conversations into smaller segments that fit the model's maximum context length. For detailed instructions to clean the ShareGPT data, check out [here](docs/commands/data_cleaning.md).
+Vicuna is created by fine-tuning a Llama base model using approximately 125K user-shared conversations gathered from ShareGPT.com with public APIs. To ensure data quality, we convert the HTML back to markdown and filter out some inappropriate or low-quality samples. Additionally, we divide lengthy conversations into smaller segments that fit the model's maximum context length. For detailed instructions to clean the ShareGPT data, check out [here](docs/commands/data_cleaning.md).
 
 We will not release the ShareGPT dataset. If you would like to try the fine-tuning code, you can run it with some dummy conversations in [dummy_conversation.json](data/dummy_conversation.json). You can follow the same format and plug in your own data.
 
@@ -295,7 +295,7 @@ We use similar hyperparameters as the Stanford Alpaca.
 pip3 install -e ".[train]"
 ```
 
-- You can use the following command to train Vicuna-7B with 4 x A100 (40GB). Update `--model_name_or_path` with the actual path to LLaMA weights and `--data_path` with the actual path to data.
+- You can use the following command to train Vicuna-7B with 4 x A100 (40GB). Update `--model_name_or_path` with the actual path to Llama weights and `--data_path` with the actual path to data.
 ```bash
 torchrun --nproc_per_node=4 --master_port=20001 fastchat/train/train_mem.py \
     --model_name_or_path meta-llama/Llama-2-7b-hf \

fastchat/__init__.py

@@ -1 +1 @@
-__version__ = "0.2.31"
+__version__ = "0.2.32"

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "fschat"
-version = "0.2.31"
+version = "0.2.32"
 description = "An open platform for training, serving, and evaluating large language model based chatbots."
 readme = "README.md"
 requires-python = ">=3.8"