update (#846)

hjh0119 · web-flow · commit d393bb4a1b7a · 2024-04-30T12:43:18.000+08:00
diff --git a/README.md b/README.md
@@ -477,6 +477,7 @@ The complete list of supported models and datasets can be found at [Supported Mo
 | WizardLM2 | [WizardLM2 series models](https://github.com/nlpxucan/WizardLM) | English | 7B-8x22B<br>including quantized versions | chat model<br>MoE model |
 | Atom | [Atom](https://github.com/LlamaFamily/Llama-Chinese) | Chinese | 7B| base model<br>chat model|
 | Chinese-LLaMA-Alpaca-2 | [Chinese-LLaMA-Alpaca-2](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2) | Chinese | 1.3B-13B| base model<br>chat model<br>long text model |
+| Chinese-LLaMA-Alpaca-3 | [Chinese-LLaMA-Alpaca-3](https://github.com/ymcui/Chinese-LLaMA-Alpaca-3) | Chinese | 8B| base model<br>chat model|
 | ModelScope-Agent | [ModelScope Agent series models](https://github.com/modelscope/modelscope-agent) | Chinese | 7B-14B| agent model |
 
 #### MLLMs
diff --git a/README_CN.md b/README_CN.md
@@ -475,6 +475,7 @@ CUDA_VISIBLE_DEVICES=0 swift deploy \
 | WizardLM2 | [WizardLM2系列模型](https://github.com/nlpxucan/WizardLM) | 多语种 | 7B-8x22B<br>包含量化版本 | chat模型<br>MoE模型 |
 | Atom | [Atom](https://github.com/LlamaFamily/Llama-Chinese) | 中文 | 7B| base模型<br>chat模型|
 | Chinese-LLaMA-Alpaca-2 | [Chinese-LLaMA-Alpaca-2](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2) | 中文 | 1.3B-13B| base模型<br>chat模型<br>长文本模型 |
+| Chinese-LLaMA-Alpaca-3 | [Chinese-LLaMA-Alpaca-3](https://github.com/ymcui/Chinese-LLaMA-Alpaca-3) | 中文 | 8B| base模型<br>chat模型|
 | ModelScope-Agent | [ModelScope Agent系列](https://github.com/modelscope/modelscope-agent) | 中文 | 7B-14B| agent模型 |
 
 
diff --git a/docs/source/LLM/支持的模型和数据集.md b/docs/source/LLM/支持的模型和数据集.md
@@ -117,6 +117,8 @@
 |chinese-alpaca-2-7b-64k|[AI-ModelScope/chinese-alpaca-2-7b-64k](https://modelscope.cn/models/AI-ModelScope/chinese-alpaca-2-7b-64k/summary)|q_proj, k_proj, v_proj|llama|&#x2714;|&#x2714;||-|[hfl/chinese-alpaca-2-7b-64k](https://huggingface.co/hfl/chinese-alpaca-2-7b-64k)|
 |chinese-alpaca-2-13b|[AI-ModelScope/chinese-alpaca-2-13b](https://modelscope.cn/models/AI-ModelScope/chinese-alpaca-2-13b/summary)|q_proj, k_proj, v_proj|llama|&#x2714;|&#x2714;||-|[hfl/chinese-alpaca-2-13b](https://huggingface.co/hfl/chinese-alpaca-2-13b)|
 |chinese-alpaca-2-13b-16k|[AI-ModelScope/chinese-alpaca-2-13b-16k](https://modelscope.cn/models/AI-ModelScope/chinese-alpaca-2-13b-16k/summary)|q_proj, k_proj, v_proj|llama|&#x2714;|&#x2714;||-|[hfl/chinese-alpaca-2-13b-16k](https://huggingface.co/hfl/chinese-alpaca-2-13b-16k)|
+|llama-3-chinese-8b|[ChineseAlpacaGroup/llama-3-chinese-8b](https://modelscope.cn/models/ChineseAlpacaGroup/llama-3-chinese-8b/summary)|q_proj, k_proj, v_proj|default-generation|&#x2714;|&#x2714;||-|[hfl/llama-3-chinese-8b](https://huggingface.co/hfl/llama-3-chinese-8b)|
+|llama-3-chinese-8b-instruct|[ChineseAlpacaGroup/llama-3-chinese-8b-instruct](https://modelscope.cn/models/ChineseAlpacaGroup/llama-3-chinese-8b-instruct/summary)|q_proj, k_proj, v_proj|llama3|&#x2714;|&#x2714;||-|[hfl/llama-3-chinese-8b-instruct](https://huggingface.co/hfl/llama-3-chinese-8b-instruct)|
 |atom-7b|[FlagAlpha/Atom-7B](https://modelscope.cn/models/FlagAlpha/Atom-7B/summary)|q_proj, k_proj, v_proj|default-generation|&#x2714;|&#x2714;||-|[FlagAlpha/Atom-7B](https://huggingface.co/FlagAlpha/Atom-7B)|
 |atom-7b-chat|[FlagAlpha/Atom-7B-Chat](https://modelscope.cn/models/FlagAlpha/Atom-7B-Chat/summary)|q_proj, k_proj, v_proj|atom|&#x2714;|&#x2714;||-|[FlagAlpha/Atom-7B-Chat](https://huggingface.co/FlagAlpha/Atom-7B-Chat)|
 |llava1d6-mistral-7b-instruct|[AI-ModelScope/llava-v1.6-mistral-7b](https://modelscope.cn/models/AI-ModelScope/llava-v1.6-mistral-7b/summary)|q_proj, k_proj, v_proj|llava-mistral-instruct|&#x2714;|&#x2718;|transformers>=4.34|multi-modal, vision|[liuhaotian/llava-v1.6-mistral-7b](https://huggingface.co/liuhaotian/llava-v1.6-mistral-7b)|
@@ -156,6 +158,7 @@
 |internlm2-math-20b|[Shanghai_AI_Laboratory/internlm2-math-base-20b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-math-base-20b/summary)|wqkv|default-generation|&#x2714;|&#x2714;|transformers>=4.35|math|[internlm/internlm2-math-base-20b](https://huggingface.co/internlm/internlm2-math-base-20b)|
 |internlm2-math-20b-chat|[Shanghai_AI_Laboratory/internlm2-math-20b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-math-20b/summary)|wqkv|internlm2|&#x2714;|&#x2714;|transformers>=4.35|math|[internlm/internlm2-math-20b](https://huggingface.co/internlm/internlm2-math-20b)|
 |internlm-xcomposer2-7b-chat|[Shanghai_AI_Laboratory/internlm-xcomposer2-7b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm-xcomposer2-7b/summary)|wqkv|internlm-xcomposer2|&#x2714;|&#x2718;||multi-modal, vision|[internlm/internlm-xcomposer2-7b](https://huggingface.co/internlm/internlm-xcomposer2-7b)|
+|internvl-chat-v1_5|[AI-ModelScope/InternVL-Chat-V1-5](https://modelscope.cn/models/AI-ModelScope/InternVL-Chat-V1-5/summary)|wqkv|internvl|&#x2714;|&#x2718;|transformers>=4.35|-|[OpenGVLab/InternVL-Chat-V1-5](https://huggingface.co/OpenGVLab/InternVL-Chat-V1-5)|
 |deepseek-7b|[deepseek-ai/deepseek-llm-7b-base](https://modelscope.cn/models/deepseek-ai/deepseek-llm-7b-base/summary)|q_proj, k_proj, v_proj|default-generation|&#x2714;|&#x2714;||-|[deepseek-ai/deepseek-llm-7b-base](https://huggingface.co/deepseek-ai/deepseek-llm-7b-base)|
 |deepseek-7b-chat|[deepseek-ai/deepseek-llm-7b-chat](https://modelscope.cn/models/deepseek-ai/deepseek-llm-7b-chat/summary)|q_proj, k_proj, v_proj|deepseek|&#x2714;|&#x2714;||-|[deepseek-ai/deepseek-llm-7b-chat](https://huggingface.co/deepseek-ai/deepseek-llm-7b-chat)|
 |deepseek-moe-16b|[deepseek-ai/deepseek-moe-16b-base](https://modelscope.cn/models/deepseek-ai/deepseek-moe-16b-base/summary)|q_proj, k_proj, v_proj|default-generation|&#x2714;|&#x2714;||-|[deepseek-ai/deepseek-moe-16b-base](https://huggingface.co/deepseek-ai/deepseek-moe-16b-base)|
@@ -250,8 +253,8 @@
 |phi3-4b-4k-instruct|[LLM-Research/Phi-3-mini-4k-instruct](https://modelscope.cn/models/LLM-Research/Phi-3-mini-4k-instruct/summary)|qkv_proj|phi3|&#x2714;|&#x2718;|transformers>=4.36|general|[microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct)|
 |phi3-4b-128k-instruct|[LLM-Research/Phi-3-mini-128k-instruct](https://modelscope.cn/models/LLM-Research/Phi-3-mini-128k-instruct/summary)|qkv_proj|phi3|&#x2714;|&#x2718;|transformers>=4.36|general|[microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct)|
 |cogvlm-17b-instruct|[ZhipuAI/cogvlm-chat](https://modelscope.cn/models/ZhipuAI/cogvlm-chat/summary)|vision_expert_query_key_value, vision_expert_dense, language_expert_query_key_value, language_expert_dense|cogvlm-instruct|&#x2718;|&#x2718;||multi-modal, vision|[THUDM/cogvlm-chat-hf](https://huggingface.co/THUDM/cogvlm-chat-hf)|
-|cogagent-18b-chat|[ZhipuAI/cogagent-chat](https://modelscope.cn/models/ZhipuAI/cogagent-chat/summary)|vision_expert_query_key_value, vision_expert_dense, language_expert_query_key_value, language_expert_dense, query, key_value, dense|cogagent-chat|&#x2718;|&#x2718;||multi-modal, vision|[THUDM/cogagent-chat-hf](https://huggingface.co/THUDM/cogagent-chat-hf)|
-|cogagent-18b-instruct|[ZhipuAI/cogagent-vqa](https://modelscope.cn/models/ZhipuAI/cogagent-vqa/summary)|vision_expert_query_key_value, vision_expert_dense, language_expert_query_key_value, language_expert_dense, query, key_value, dense|cogagent-instruct|&#x2718;|&#x2718;||multi-modal, vision|[THUDM/cogagent-vqa-hf](https://huggingface.co/THUDM/cogagent-vqa-hf)|
+|cogagent-18b-chat|[ZhipuAI/cogagent-chat](https://modelscope.cn/models/ZhipuAI/cogagent-chat/summary)|vision_expert_query_key_value, vision_expert_dense, language_expert_query_key_value, language_expert_dense, query, key_value, dense|cogagent-chat|&#x2718;|&#x2718;|timm|multi-modal, vision|[THUDM/cogagent-chat-hf](https://huggingface.co/THUDM/cogagent-chat-hf)|
+|cogagent-18b-instruct|[ZhipuAI/cogagent-vqa](https://modelscope.cn/models/ZhipuAI/cogagent-vqa/summary)|vision_expert_query_key_value, vision_expert_dense, language_expert_query_key_value, language_expert_dense, query, key_value, dense|cogagent-instruct|&#x2718;|&#x2718;|timm|multi-modal, vision|[THUDM/cogagent-vqa-hf](https://huggingface.co/THUDM/cogagent-vqa-hf)|
 |mamba-130m|[AI-ModelScope/mamba-130m-hf](https://modelscope.cn/models/AI-ModelScope/mamba-130m-hf/summary)|in_proj, x_proj, embeddings, out_proj|default-generation|&#x2718;|&#x2718;|transformers>=4.39.0|-|[state-spaces/mamba-130m-hf](https://huggingface.co/state-spaces/mamba-130m-hf)|
 |mamba-370m|[AI-ModelScope/mamba-370m-hf](https://modelscope.cn/models/AI-ModelScope/mamba-370m-hf/summary)|in_proj, x_proj, embeddings, out_proj|default-generation|&#x2718;|&#x2718;|transformers>=4.39.0|-|[state-spaces/mamba-370m-hf](https://huggingface.co/state-spaces/mamba-370m-hf)|
 |mamba-390m|[AI-ModelScope/mamba-390m-hf](https://modelscope.cn/models/AI-ModelScope/mamba-390m-hf/summary)|in_proj, x_proj, embeddings, out_proj|default-generation|&#x2718;|&#x2718;|transformers>=4.39.0|-|[state-spaces/mamba-390m-hf](https://huggingface.co/state-spaces/mamba-390m-hf)|
diff --git a/docs/source_en/LLM/Supported-models-datasets.md b/docs/source_en/LLM/Supported-models-datasets.md
@@ -117,6 +117,8 @@ The table below introcudes all models supported by SWIFT:
 |chinese-alpaca-2-7b-64k|[AI-ModelScope/chinese-alpaca-2-7b-64k](https://modelscope.cn/models/AI-ModelScope/chinese-alpaca-2-7b-64k/summary)|q_proj, k_proj, v_proj|llama|&#x2714;|&#x2714;||-|[hfl/chinese-alpaca-2-7b-64k](https://huggingface.co/hfl/chinese-alpaca-2-7b-64k)|
 |chinese-alpaca-2-13b|[AI-ModelScope/chinese-alpaca-2-13b](https://modelscope.cn/models/AI-ModelScope/chinese-alpaca-2-13b/summary)|q_proj, k_proj, v_proj|llama|&#x2714;|&#x2714;||-|[hfl/chinese-alpaca-2-13b](https://huggingface.co/hfl/chinese-alpaca-2-13b)|
 |chinese-alpaca-2-13b-16k|[AI-ModelScope/chinese-alpaca-2-13b-16k](https://modelscope.cn/models/AI-ModelScope/chinese-alpaca-2-13b-16k/summary)|q_proj, k_proj, v_proj|llama|&#x2714;|&#x2714;||-|[hfl/chinese-alpaca-2-13b-16k](https://huggingface.co/hfl/chinese-alpaca-2-13b-16k)|
+|llama-3-chinese-8b|[ChineseAlpacaGroup/llama-3-chinese-8b](https://modelscope.cn/models/ChineseAlpacaGroup/llama-3-chinese-8b/summary)|q_proj, k_proj, v_proj|default-generation|&#x2714;|&#x2714;||-|[hfl/llama-3-chinese-8b](https://huggingface.co/hfl/llama-3-chinese-8b)|
+|llama-3-chinese-8b-instruct|[ChineseAlpacaGroup/llama-3-chinese-8b-instruct](https://modelscope.cn/models/ChineseAlpacaGroup/llama-3-chinese-8b-instruct/summary)|q_proj, k_proj, v_proj|llama3|&#x2714;|&#x2714;||-|[hfl/llama-3-chinese-8b-instruct](https://huggingface.co/hfl/llama-3-chinese-8b-instruct)|
 |atom-7b|[FlagAlpha/Atom-7B](https://modelscope.cn/models/FlagAlpha/Atom-7B/summary)|q_proj, k_proj, v_proj|default-generation|&#x2714;|&#x2714;||-|[FlagAlpha/Atom-7B](https://huggingface.co/FlagAlpha/Atom-7B)|
 |atom-7b-chat|[FlagAlpha/Atom-7B-Chat](https://modelscope.cn/models/FlagAlpha/Atom-7B-Chat/summary)|q_proj, k_proj, v_proj|atom|&#x2714;|&#x2714;||-|[FlagAlpha/Atom-7B-Chat](https://huggingface.co/FlagAlpha/Atom-7B-Chat)|
 |llava1d6-mistral-7b-instruct|[AI-ModelScope/llava-v1.6-mistral-7b](https://modelscope.cn/models/AI-ModelScope/llava-v1.6-mistral-7b/summary)|q_proj, k_proj, v_proj|llava-mistral-instruct|&#x2714;|&#x2718;|transformers>=4.34|multi-modal, vision|[liuhaotian/llava-v1.6-mistral-7b](https://huggingface.co/liuhaotian/llava-v1.6-mistral-7b)|
@@ -156,6 +158,7 @@ The table below introcudes all models supported by SWIFT:
 |internlm2-math-20b|[Shanghai_AI_Laboratory/internlm2-math-base-20b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-math-base-20b/summary)|wqkv|default-generation|&#x2714;|&#x2714;|transformers>=4.35|math|[internlm/internlm2-math-base-20b](https://huggingface.co/internlm/internlm2-math-base-20b)|
 |internlm2-math-20b-chat|[Shanghai_AI_Laboratory/internlm2-math-20b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-math-20b/summary)|wqkv|internlm2|&#x2714;|&#x2714;|transformers>=4.35|math|[internlm/internlm2-math-20b](https://huggingface.co/internlm/internlm2-math-20b)|
 |internlm-xcomposer2-7b-chat|[Shanghai_AI_Laboratory/internlm-xcomposer2-7b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm-xcomposer2-7b/summary)|wqkv|internlm-xcomposer2|&#x2714;|&#x2718;||multi-modal, vision|[internlm/internlm-xcomposer2-7b](https://huggingface.co/internlm/internlm-xcomposer2-7b)|
+|internvl-chat-v1_5|[AI-ModelScope/InternVL-Chat-V1-5](https://modelscope.cn/models/AI-ModelScope/InternVL-Chat-V1-5/summary)|wqkv|internvl|&#x2714;|&#x2718;|transformers>=4.35|-|[OpenGVLab/InternVL-Chat-V1-5](https://huggingface.co/OpenGVLab/InternVL-Chat-V1-5)|
 |deepseek-7b|[deepseek-ai/deepseek-llm-7b-base](https://modelscope.cn/models/deepseek-ai/deepseek-llm-7b-base/summary)|q_proj, k_proj, v_proj|default-generation|&#x2714;|&#x2714;||-|[deepseek-ai/deepseek-llm-7b-base](https://huggingface.co/deepseek-ai/deepseek-llm-7b-base)|
 |deepseek-7b-chat|[deepseek-ai/deepseek-llm-7b-chat](https://modelscope.cn/models/deepseek-ai/deepseek-llm-7b-chat/summary)|q_proj, k_proj, v_proj|deepseek|&#x2714;|&#x2714;||-|[deepseek-ai/deepseek-llm-7b-chat](https://huggingface.co/deepseek-ai/deepseek-llm-7b-chat)|
 |deepseek-moe-16b|[deepseek-ai/deepseek-moe-16b-base](https://modelscope.cn/models/deepseek-ai/deepseek-moe-16b-base/summary)|q_proj, k_proj, v_proj|default-generation|&#x2714;|&#x2714;||-|[deepseek-ai/deepseek-moe-16b-base](https://huggingface.co/deepseek-ai/deepseek-moe-16b-base)|
@@ -250,8 +253,8 @@ The table below introcudes all models supported by SWIFT:
 |phi3-4b-4k-instruct|[LLM-Research/Phi-3-mini-4k-instruct](https://modelscope.cn/models/LLM-Research/Phi-3-mini-4k-instruct/summary)|qkv_proj|phi3|&#x2714;|&#x2718;|transformers>=4.36|general|[microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct)|
 |phi3-4b-128k-instruct|[LLM-Research/Phi-3-mini-128k-instruct](https://modelscope.cn/models/LLM-Research/Phi-3-mini-128k-instruct/summary)|qkv_proj|phi3|&#x2714;|&#x2718;|transformers>=4.36|general|[microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct)|
 |cogvlm-17b-instruct|[ZhipuAI/cogvlm-chat](https://modelscope.cn/models/ZhipuAI/cogvlm-chat/summary)|vision_expert_query_key_value, vision_expert_dense, language_expert_query_key_value, language_expert_dense|cogvlm-instruct|&#x2718;|&#x2718;||multi-modal, vision|[THUDM/cogvlm-chat-hf](https://huggingface.co/THUDM/cogvlm-chat-hf)|
-|cogagent-18b-chat|[ZhipuAI/cogagent-chat](https://modelscope.cn/models/ZhipuAI/cogagent-chat/summary)|vision_expert_query_key_value, vision_expert_dense, language_expert_query_key_value, language_expert_dense, query, key_value, dense|cogagent-chat|&#x2718;|&#x2718;||multi-modal, vision|[THUDM/cogagent-chat-hf](https://huggingface.co/THUDM/cogagent-chat-hf)|
-|cogagent-18b-instruct|[ZhipuAI/cogagent-vqa](https://modelscope.cn/models/ZhipuAI/cogagent-vqa/summary)|vision_expert_query_key_value, vision_expert_dense, language_expert_query_key_value, language_expert_dense, query, key_value, dense|cogagent-instruct|&#x2718;|&#x2718;||multi-modal, vision|[THUDM/cogagent-vqa-hf](https://huggingface.co/THUDM/cogagent-vqa-hf)|
+|cogagent-18b-chat|[ZhipuAI/cogagent-chat](https://modelscope.cn/models/ZhipuAI/cogagent-chat/summary)|vision_expert_query_key_value, vision_expert_dense, language_expert_query_key_value, language_expert_dense, query, key_value, dense|cogagent-chat|&#x2718;|&#x2718;|timm|multi-modal, vision|[THUDM/cogagent-chat-hf](https://huggingface.co/THUDM/cogagent-chat-hf)|
+|cogagent-18b-instruct|[ZhipuAI/cogagent-vqa](https://modelscope.cn/models/ZhipuAI/cogagent-vqa/summary)|vision_expert_query_key_value, vision_expert_dense, language_expert_query_key_value, language_expert_dense, query, key_value, dense|cogagent-instruct|&#x2718;|&#x2718;|timm|multi-modal, vision|[THUDM/cogagent-vqa-hf](https://huggingface.co/THUDM/cogagent-vqa-hf)|
 |mamba-130m|[AI-ModelScope/mamba-130m-hf](https://modelscope.cn/models/AI-ModelScope/mamba-130m-hf/summary)|in_proj, x_proj, embeddings, out_proj|default-generation|&#x2718;|&#x2718;|transformers>=4.39.0|-|[state-spaces/mamba-130m-hf](https://huggingface.co/state-spaces/mamba-130m-hf)|
 |mamba-370m|[AI-ModelScope/mamba-370m-hf](https://modelscope.cn/models/AI-ModelScope/mamba-370m-hf/summary)|in_proj, x_proj, embeddings, out_proj|default-generation|&#x2718;|&#x2718;|transformers>=4.39.0|-|[state-spaces/mamba-370m-hf](https://huggingface.co/state-spaces/mamba-370m-hf)|
 |mamba-390m|[AI-ModelScope/mamba-390m-hf](https://modelscope.cn/models/AI-ModelScope/mamba-390m-hf/summary)|in_proj, x_proj, embeddings, out_proj|default-generation|&#x2718;|&#x2718;|transformers>=4.39.0|-|[state-spaces/mamba-390m-hf](https://huggingface.co/state-spaces/mamba-390m-hf)|
diff --git a/swift/llm/utils/model.py b/swift/llm/utils/model.py
@@ -143,7 +143,7 @@ class ModelType:
     llama3_70b_instruct_int4 = 'llama3-70b-instruct-int4'
     llama3_70b_instruct_int8 = 'llama3-70b-instruct-int8'
     llama3_70b_instruct_awq = 'llama3-70b-instruct-awq'
-    # chinese-llama-alpaca-2
+    # chinese-llama-alpaca
     chinese_llama_2_1_3b = 'chinese-llama-2-1_3b'
     chinese_llama_2_7b = 'chinese-llama-2-7b'
     chinese_llama_2_7b_16k = 'chinese-llama-2-7b-16k'
@@ -156,6 +156,8 @@ class ModelType:
     chinese_alpaca_2_7b_64k = 'chinese-alpaca-2-7b-64k'
     chinese_alpaca_2_13b = 'chinese-alpaca-2-13b'
     chinese_alpaca_2_13b_16k = 'chinese-alpaca-2-13b-16k'
+    llama_3_chinese_8b = 'llama-3-chinese-8b'
+    llama_3_chinese_8b_instruct = 'llama-3-chinese-8b-instruct'
     # atom
     atom_7b = 'atom-7b'
     atom_7b_chat = 'atom-7b-chat'
@@ -2878,6 +2880,22 @@ def get_model_tokenizer_deepseek_vl(model_dir: str,
     support_flash_attn=True,
     support_vllm=True,
     hf_model_id='meta-llama/Meta-Llama-3-8B')
+@register_model(
+    ModelType.llama_3_chinese_8b,
+    'ChineseAlpacaGroup/llama-3-chinese-8b',
+    LoRATM.llama2,
+    TemplateType.default_generation,
+    support_flash_attn=True,
+    support_vllm=True,
+    hf_model_id='hfl/llama-3-chinese-8b')
+@register_model(
+    ModelType.llama_3_chinese_8b_instruct,
+    'ChineseAlpacaGroup/llama-3-chinese-8b-instruct',
+    LoRATM.llama2,
+    TemplateType.llama3,
+    support_flash_attn=True,
+    support_vllm=True,
+    hf_model_id='hfl/llama-3-chinese-8b-instruct')
 @register_model(
     ModelType.llama2_7b_aqlm_2bit_1x16,
     'AI-ModelScope/Llama-2-7b-AQLM-2Bit-1x16-hf',
