Skip to content

PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度

correct errors of deepseek-r1-0528 recipes (#591)

Heng Guo6783fc505c22
diff --git a/docs/DeepSeek-R1-0528-int4-asym-awq-inc.md b/docs/DeepSeek-R1-0528-int4-asym-awq-inc.md
index d57643c75..7215ef906 100644
--- a/docs/DeepSeek-R1-0528-int4-asym-awq-inc.md
+++ b/docs/DeepSeek-R1-0528-int4-asym-awq-inc.md
@@ -7,9 +7,9 @@ base_model:
## Model Details
-This model is an int4 model with group_size 64 and symmetric quantization of [deepseek-ai/DeepSeek-R1-0528](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528) generated by [intel/auto-round](https://github.com/intel/auto-round) algorithm. Some layers are fallback to 4/16 bits. Refer to Section "Generate the model" for more details of mixed bits setting.
+This model is an int4 model with group_size 64 and asymmetric quantization of [deepseek-ai/DeepSeek-R1-0528](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528) generated by [intel/auto-round](https://github.com/intel/auto-round) algorithm.
-Please follow the license of the original model. This model could **NOT** run on other severing frameworks.
+Please follow the license of the original model.
## How To Use
diff --git a/docs/DeepSeek-R1-0528-int4-sym-gptq-inc.md b/docs/DeepSeek-R1-0528-int4-sym-gptq-inc.md
index 670773d6f..4debd8337 100644
--- a/docs/DeepSeek-R1-0528-int4-sym-gptq-inc.md
+++ b/docs/DeepSeek-R1-0528-int4-sym-gptq-inc.md
@@ -7,9 +7,9 @@ base_model:
## Model Details
-This model is an int4 model with group_size 64 and symmetric quantization of [deepseek-ai/DeepSeek-R1-0528](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528) generated by [intel/auto-round](https://github.com/intel/auto-round) algorithm. Some layers are fallback to 4/16 bits. Refer to Section "Generate the model" for more details of mixed bits setting.
+This model is an int4 model with group_size 64 and symmetric quantization of [deepseek-ai/DeepSeek-R1-0528](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528) generated by [intel/auto-round](https://github.com/intel/auto-round) algorithm.
-Please follow the license of the original model. This model could **NOT** run on other severing frameworks.
+Please follow the license of the original model.
## How To Use