docs(README): typo (#56)

README.md

@@ -43,7 +43,7 @@ LMDeploy is a toolkit for compressing, deploying, and serving LLM, developed by
   <img src="https://github.com/NVIDIA/FasterTransformer/blob/main/docs/images/gpt/gpt_interactive_generation.2.png?raw=true"/>
 </div>
 
-- **Multi-GPU Model Deployment and Quantization**: We provide comprehensive support for model deployment and quantization, and have successfully validated it on models ranging from 7B to 100B parameters.
+- **Multi-GPU Model Deployment and Quantization**: We provide comprehensive model deployment and quantification support, and have been validated at different scales.
 
 - **Persistent Batch Inference**: Further optimization of model execution efficiency.
 
@@ -155,16 +155,12 @@ In fp16 mode, kv_cache int8 quantization can be enabled, and a single card can s
 First execute the quantization script, and the quantization parameters are stored in the weight directory transformed by `deploy.py`.
 
 ```
-
-
 python3 -m lmdeploy.lite.apis.kv_qparams \
   --model $HF_MODEL \
   --output_dir $DEPLOY_WEIGHT_DIR \
   --symmetry True \   # Whether to use symmetric or asymmetric quantization.
   --offload  False \  # Whether to offload some modules to CPU to save GPU memory.
   --num_tp 1 \   # The number of GPUs used for tensor parallelism
-
-
 ```
 
 Then adjust `config.ini`

docs/zh_cn/quantization.md

@@ -37,7 +37,7 @@
 3. 执行量化脚本，得到量化参数，放到 weights 目录；修改配置文件，使 [kCacheKVInt8](../../src/turbomind/models/llama/llama_utils.h) 选项生效
 4. 再次执行 `client.py`，读取 int8 版本精度
 
-以下是 `kCacheKVInt8` 方法仅用 c4 数据集量化，在 mmlu-social-science 数据集的精度损失。
+以下是 `kCacheKVInt8` 方法仅从 c4 数据集，随机选择 128 条数据量化，在 mmlu-social-science 数据集的精度损失。
 
 | task |       dataset       | metric | fp16  | int8  | diff  |
 | :--: | :-----------------: | :----: | :---: | :---: | :---: |