Skip to content

Commit

Permalink
support qwen110b gptq int4 (#818)
Browse files Browse the repository at this point in the history
  • Loading branch information
@Jintao-Huang
Jintao-Huang authored Apr 27, 2024
1 parent 0247075 commit 052d4f1
Show file tree
Hide file tree
Showing 3 changed files with 14 additions and 0 deletions.
1 change: 1 addition & 0 deletions docs/source/LLM/支持的模型和数据集.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -59,6 +59,7 @@
|qwen1half-14b-chat-int4|[qwen/Qwen1.5-14B-Chat-GPTQ-Int4](https://modelscope.cn/models/qwen/Qwen1.5-14B-Chat-GPTQ-Int4/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|-|[Qwen/Qwen1.5-14B-Chat-GPTQ-Int4](https://huggingface.co/Qwen/Qwen1.5-14B-Chat-GPTQ-Int4)|
|qwen1half-32b-chat-int4|[qwen/Qwen1.5-32B-Chat-GPTQ-Int4](https://modelscope.cn/models/qwen/Qwen1.5-32B-Chat-GPTQ-Int4/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|-|[Qwen/Qwen1.5-32B-Chat-GPTQ-Int4](https://huggingface.co/Qwen/Qwen1.5-32B-Chat-GPTQ-Int4)|
|qwen1half-72b-chat-int4|[qwen/Qwen1.5-72B-Chat-GPTQ-Int4](https://modelscope.cn/models/qwen/Qwen1.5-72B-Chat-GPTQ-Int4/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|-|[Qwen/Qwen1.5-72B-Chat-GPTQ-Int4](https://huggingface.co/Qwen/Qwen1.5-72B-Chat-GPTQ-Int4)|
|qwen1half-110b-chat-int4|[qwen/Qwen1.5-110B-Chat-GPTQ-Int4](https://modelscope.cn/models/qwen/Qwen1.5-110B-Chat-GPTQ-Int4/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|-|[Qwen/Qwen1.5-110B-Chat-GPTQ-Int4](https://huggingface.co/Qwen/Qwen1.5-110B-Chat-GPTQ-Int4)|
|qwen1half-0_5b-chat-int8|[qwen/Qwen1.5-0.5B-Chat-GPTQ-Int8](https://modelscope.cn/models/qwen/Qwen1.5-0.5B-Chat-GPTQ-Int8/summary)|q_proj, k_proj, v_proj|qwen|✔|✘|auto_gptq>=0.5, transformers>=4.37|-|[Qwen/Qwen1.5-0.5B-Chat-GPTQ-Int8](https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat-GPTQ-Int8)|
|qwen1half-1_8b-chat-int8|[qwen/Qwen1.5-1.8B-Chat-GPTQ-Int8](https://modelscope.cn/models/qwen/Qwen1.5-1.8B-Chat-GPTQ-Int8/summary)|q_proj, k_proj, v_proj|qwen|✔|✘|auto_gptq>=0.5, transformers>=4.37|-|[Qwen/Qwen1.5-1.8B-Chat-GPTQ-Int8](https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat-GPTQ-Int8)|
|qwen1half-4b-chat-int8|[qwen/Qwen1.5-4B-Chat-GPTQ-Int8](https://modelscope.cn/models/qwen/Qwen1.5-4B-Chat-GPTQ-Int8/summary)|q_proj, k_proj, v_proj|qwen|✔|✘|auto_gptq>=0.5, transformers>=4.37|-|[Qwen/Qwen1.5-4B-Chat-GPTQ-Int8](https://huggingface.co/Qwen/Qwen1.5-4B-Chat-GPTQ-Int8)|
Expand Down
1 change: 1 addition & 0 deletions docs/source_en/LLM/Supported-models-datasets.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -59,6 +59,7 @@ The table below introcudes all models supported by SWIFT:
|qwen1half-14b-chat-int4|[qwen/Qwen1.5-14B-Chat-GPTQ-Int4](https://modelscope.cn/models/qwen/Qwen1.5-14B-Chat-GPTQ-Int4/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|-|[Qwen/Qwen1.5-14B-Chat-GPTQ-Int4](https://huggingface.co/Qwen/Qwen1.5-14B-Chat-GPTQ-Int4)|
|qwen1half-32b-chat-int4|[qwen/Qwen1.5-32B-Chat-GPTQ-Int4](https://modelscope.cn/models/qwen/Qwen1.5-32B-Chat-GPTQ-Int4/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|-|[Qwen/Qwen1.5-32B-Chat-GPTQ-Int4](https://huggingface.co/Qwen/Qwen1.5-32B-Chat-GPTQ-Int4)|
|qwen1half-72b-chat-int4|[qwen/Qwen1.5-72B-Chat-GPTQ-Int4](https://modelscope.cn/models/qwen/Qwen1.5-72B-Chat-GPTQ-Int4/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|-|[Qwen/Qwen1.5-72B-Chat-GPTQ-Int4](https://huggingface.co/Qwen/Qwen1.5-72B-Chat-GPTQ-Int4)|
|qwen1half-110b-chat-int4|[qwen/Qwen1.5-110B-Chat-GPTQ-Int4](https://modelscope.cn/models/qwen/Qwen1.5-110B-Chat-GPTQ-Int4/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|-|[Qwen/Qwen1.5-110B-Chat-GPTQ-Int4](https://huggingface.co/Qwen/Qwen1.5-110B-Chat-GPTQ-Int4)|
|qwen1half-0_5b-chat-int8|[qwen/Qwen1.5-0.5B-Chat-GPTQ-Int8](https://modelscope.cn/models/qwen/Qwen1.5-0.5B-Chat-GPTQ-Int8/summary)|q_proj, k_proj, v_proj|qwen|✔|✘|auto_gptq>=0.5, transformers>=4.37|-|[Qwen/Qwen1.5-0.5B-Chat-GPTQ-Int8](https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat-GPTQ-Int8)|
|qwen1half-1_8b-chat-int8|[qwen/Qwen1.5-1.8B-Chat-GPTQ-Int8](https://modelscope.cn/models/qwen/Qwen1.5-1.8B-Chat-GPTQ-Int8/summary)|q_proj, k_proj, v_proj|qwen|✔|✘|auto_gptq>=0.5, transformers>=4.37|-|[Qwen/Qwen1.5-1.8B-Chat-GPTQ-Int8](https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat-GPTQ-Int8)|
|qwen1half-4b-chat-int8|[qwen/Qwen1.5-4B-Chat-GPTQ-Int8](https://modelscope.cn/models/qwen/Qwen1.5-4B-Chat-GPTQ-Int8/summary)|q_proj, k_proj, v_proj|qwen|✔|✘|auto_gptq>=0.5, transformers>=4.37|-|[Qwen/Qwen1.5-4B-Chat-GPTQ-Int8](https://huggingface.co/Qwen/Qwen1.5-4B-Chat-GPTQ-Int8)|
Expand Down
12 changes: 12 additions & 0 deletions swift/llm/utils/model.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -89,6 +89,7 @@ class ModelType:
qwen1half_14b_chat_int4 = 'qwen1half-14b-chat-int4'
qwen1half_32b_chat_int4 = 'qwen1half-32b-chat-int4'
qwen1half_72b_chat_int4 = 'qwen1half-72b-chat-int4'
qwen1half_110b_chat_int4 = 'qwen1half-110b-chat-int4'
qwen1half_0_5b_chat_int8 = 'qwen1half-0_5b-chat-int8'
qwen1half_1_8b_chat_int8 = 'qwen1half-1_8b-chat-int8'
qwen1half_4b_chat_int8 = 'qwen1half-4b-chat-int8'
Expand Down Expand Up @@ -2232,6 +2233,17 @@ def get_model_tokenizer_qwen1half(model_dir: str,
support_flash_attn=True,
support_vllm=True,
hf_model_id='Qwen/Qwen1.5-72B-Chat-GPTQ-Int4')
@register_model(
ModelType.qwen1half_110b_chat_int4,
'qwen/Qwen1.5-110B-Chat-GPTQ-Int4',
LoRATM.qwen1half,
TemplateType.qwen,
requires=['auto_gptq>=0.5', 'transformers>=4.37'],
torch_dtype=torch.float16,
function_kwargs={'gptq_bits': 4},
support_flash_attn=True,
support_vllm=True,
hf_model_id='Qwen/Qwen1.5-110B-Chat-GPTQ-Int4')
@register_model(
ModelType.qwen1half_72b_chat_int8,
'qwen/Qwen1.5-72B-Chat-GPTQ-Int8',
Expand Down

0 comments on commit 052d4f1

Please sign in to comment.