|
55 | 55 | ], |
56 | 56 | allow_china_region=True, |
57 | 57 | huggingface_model_id="deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", |
58 | | - # modelscope_model_id="Qwen/Qwen2.5-32B-Instruct", |
| 58 | + modelscope_model_id="deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", |
59 | 59 | require_huggingface_token=False, |
60 | 60 | application_scenario="Agent, tool use, translation, summary", |
61 | 61 | description="The latest series of DeepSeek LLMs for reasoning", |
|
85 | 85 | ], |
86 | 86 | allow_china_region=True, |
87 | 87 | huggingface_model_id="deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", |
88 | | - # modelscope_model_id="Qwen/Qwen2.5-14B-Instruct", |
| 88 | + modelscope_model_id="deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", |
89 | 89 | require_huggingface_token=False, |
90 | 90 | application_scenario="Agent, tool use, translation, summary", |
91 | 91 | description="The latest series of DeepSeek LLMs for reasoning", |
|
116 | 116 | ], |
117 | 117 | allow_china_region=True, |
118 | 118 | huggingface_model_id="deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", |
119 | | - # modelscope_model_id="Qwen/Qwen2.5-14B-Instruct", |
| 119 | + modelscope_model_id="deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", |
120 | 120 | require_huggingface_token=False, |
121 | 121 | application_scenario="Agent, tool use, translation, summary", |
122 | 122 | description="The latest series of DeepSeek LLMs for reasoning", |
|
147 | 147 | ], |
148 | 148 | allow_china_region=True, |
149 | 149 | huggingface_model_id="deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B", |
150 | | - # modelscope_model_id="Qwen/Qwen2.5-14B-Instruct", |
| 150 | + modelscope_model_id="deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B", |
151 | 151 | require_huggingface_token=False, |
152 | 152 | application_scenario="Agent, tool use, translation, summary", |
153 | 153 | description="The latest series of DeepSeek LLMs for reasoning", |
|
244 | 244 | ], |
245 | 245 | allow_china_region=True, |
246 | 246 | huggingface_model_id="deepseek-ai/DeepSeek-R1-Distill-Llama-8B", |
247 | | - # modelscope_model_id="Qwen/Qwen2.5-14B-Instruct", |
| 247 | + modelscope_model_id="deepseek-ai/DeepSeek-R1-Distill-Llama-8B", |
248 | 248 | require_huggingface_token=False, |
249 | 249 | application_scenario="Agent, tool use, translation, summary", |
250 | 250 | description="The latest series of DeepSeek LLMs for reasoning", |
|
0 commit comments