docs(serving.md): typo (#92)

* docs(serving.md): typo

* docs(README): quantization

README.md

@@ -148,7 +148,7 @@ deepspeed --module --num_gpus 2 lmdeploy.pytorch.chat \
 ## Quantization
 
 In fp16 mode, kv_cache int8 quantization can be enabled, and a single card can serve more users.
-First execute the quantization script, and the quantization parameters are stored in the weight directory transformed by `deploy.py`.
+First execute the quantization script, and the quantization parameters are stored in the `workspace/triton_models/weights` transformed by `deploy.py`.
 
 ```
 python3 -m lmdeploy.lite.apis.kv_qparams \
@@ -159,7 +159,7 @@ python3 -m lmdeploy.lite.apis.kv_qparams \
   --num_tp 1 \   # The number of GPUs used for tensor parallelism
 ```
 
-Then adjust `config.ini`
+Then adjust `workspace/triton_models/weights/config.ini`
 
 - `use_context_fmha` changed to 0, means off
 - `quant_policy` is set to 4. This parameter defaults to 0, which means it is not enabled

README_zh-CN.md

@@ -147,7 +147,7 @@ deepspeed --module --num_gpus 2 lmdeploy.pytorch.chat \
 ## 量化部署
 
 在 fp16 模式下，可以开启 kv_cache int8 量化，单卡可服务更多用户。
-首先执行量化脚本，量化参数存放到 `deploy.py` 转换的 weight 目录下。
+首先执行量化脚本，量化参数存放到 `deploy.py` 转换的 `workspace/triton_models/weights` 目录下。
 
 ```
 python3 -m lmdeploy.lite.apis.kv_qparams \
@@ -158,7 +158,7 @@ python3 -m lmdeploy.lite.apis.kv_qparams \
   --num_tp 1  \  # Tensor 并行使用的 GPU 数，和 deploy.py 保持一致
 ```
 
-然后调整 `config.ini`
+然后调整 `workspace/triton_models/weights/config.ini`
 
 - `use_context_fmha` 改为 0，表示关闭
 - `quant_policy` 设置为 4。此参数默认为 0，表示不开启

docs/en/serving.md

@@ -41,7 +41,7 @@ bash workspace/service_docker_up.sh
 <summary><b>65B</b></summary>
 
 ```shell
-python3 lmdeploy.serve.turbomind.deploy llama-13B /path/to/llama-13b llama \
+python3 lmdeploy.serve.turbomind.deploy llama-65B /path/to/llama-65b llama \
     --tokenizer_path /path/to/tokenizer/model --tp 8
 bash workspace/service_docker_up.sh
 ```

docs/zh_cn/serving.md

@@ -41,7 +41,7 @@ bash workspace/service_docker_up.sh
 <summary><b>65B</b></summary>
 
 ```shell
-python3 lmdeploy.serve.turbomind.deploy llama-13B /path/to/llama-13b llama \
+python3 lmdeploy.serve.turbomind.deploy llama-65B /path/to/llama-65b llama \
     --tokenizer_path /path/to/tokenizer/model --tp 8
 bash workspace/service_docker_up.sh
 ```