@@ -136,21 +136,21 @@ The table below introcudes all models supported by SWIFT:
136136| internlm-7b-chat-8k| [ Shanghai_AI_Laboratory/internlm-chat-7b-8k] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm-chat-7b-8k/summary ) | q_proj, k_proj, v_proj| internlm| ✘ ; | ✔ ; || -| -|
137137| internlm-20b| [ Shanghai_AI_Laboratory/internlm-20b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm-20b/summary ) | q_proj, k_proj, v_proj| default-generation-bos| ✘ ; | ✔ ; || -| [ internlm/internlm2-20b] ( https://huggingface.co/internlm/internlm2-20b ) |
138138| internlm-20b-chat| [ Shanghai_AI_Laboratory/internlm-chat-20b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm-chat-20b/summary ) | q_proj, k_proj, v_proj| internlm| ✘ ; | ✔ ; || -| [ internlm/internlm2-chat-20b] ( https://huggingface.co/internlm/internlm2-chat-20b ) |
139- | internlm2-1_8b| [ Shanghai_AI_Laboratory/internlm2-1_8b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-1_8b/summary ) | wqkv| default-generation-bos| ✔ ; | ✔ ; || -| [ internlm/internlm2-1_8b] ( https://huggingface.co/internlm/internlm2-1_8b ) |
140- | internlm2-1_8b-sft-chat| [ Shanghai_AI_Laboratory/internlm2-chat-1_8b-sft] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-1_8b-sft/summary ) | wqkv| internlm2| ✔ ; | ✔ ; || -| [ internlm/internlm2-chat-1_8b-sft] ( https://huggingface.co/internlm/internlm2-chat-1_8b-sft ) |
141- | internlm2-1_8b-chat| [ Shanghai_AI_Laboratory/internlm2-chat-1_8b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-1_8b/summary ) | wqkv| internlm2| ✔ ; | ✔ ; || -| [ internlm/internlm2-chat-1_8b] ( https://huggingface.co/internlm/internlm2-chat-1_8b ) |
142- | internlm2-7b-base| [ Shanghai_AI_Laboratory/internlm2-base-7b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-base-7b/summary ) | wqkv| default-generation-bos| ✔ ; | ✔ ; || -| [ internlm/internlm2-base-7b] ( https://huggingface.co/internlm/internlm2-base-7b ) |
143- | internlm2-7b| [ Shanghai_AI_Laboratory/internlm2-7b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-7b/summary ) | wqkv| default-generation-bos| ✔ ; | ✔ ; || -| [ internlm/internlm2-7b] ( https://huggingface.co/internlm/internlm2-7b ) |
144- | internlm2-7b-sft-chat| [ Shanghai_AI_Laboratory/internlm2-chat-7b-sft] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-7b-sft/summary ) | wqkv| internlm2| ✔ ; | ✔ ; || -| [ internlm/internlm2-chat-7b-sft] ( https://huggingface.co/internlm/internlm2-chat-7b-sft ) |
145- | internlm2-7b-chat| [ Shanghai_AI_Laboratory/internlm2-chat-7b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-7b/summary ) | wqkv| internlm2| ✔ ; | ✔ ; || -| [ internlm/internlm2-chat-7b] ( https://huggingface.co/internlm/internlm2-chat-7b ) |
146- | internlm2-20b-base| [ Shanghai_AI_Laboratory/internlm2-base-20b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-base-20b/summary ) | wqkv| default-generation-bos| ✔ ; | ✔ ; || -| [ internlm/internlm2-base-20b] ( https://huggingface.co/internlm/internlm2-base-20b ) |
147- | internlm2-20b| [ Shanghai_AI_Laboratory/internlm2-20b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-20b/summary ) | wqkv| default-generation-bos| ✔ ; | ✔ ; || -| [ internlm/internlm2-20b] ( https://huggingface.co/internlm/internlm2-20b ) |
148- | internlm2-20b-sft-chat| [ Shanghai_AI_Laboratory/internlm2-chat-20b-sft] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-20b-sft/summary ) | wqkv| internlm2| ✔ ; | ✔ ; || -| [ internlm/internlm2-chat-20b-sft] ( https://huggingface.co/internlm/internlm2-chat-20b-sft ) |
149- | internlm2-20b-chat| [ Shanghai_AI_Laboratory/internlm2-chat-20b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-20b/summary ) | wqkv| internlm2| ✔ ; | ✔ ; || -| [ internlm/internlm2-chat-20b] ( https://huggingface.co/internlm/internlm2-chat-20b ) |
150- | internlm2-math-7b| [ Shanghai_AI_Laboratory/internlm2-math-base-7b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-math-base-7b/summary ) | wqkv| default-generation-bos| ✔ ; | ✔ ; || math| [ internlm/internlm2-math-base-7b] ( https://huggingface.co/internlm/internlm2-math-base-7b ) |
151- | internlm2-math-7b-chat| [ Shanghai_AI_Laboratory/internlm2-math-7b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-math-7b/summary ) | wqkv| internlm2| ✔ ; | ✔ ; || math| [ internlm/internlm2-math-7b] ( https://huggingface.co/internlm/internlm2-math-7b ) |
152- | 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-bos| ✔ ; | ✔ ; || math| [ internlm/internlm2-math-base-20b] ( https://huggingface.co/internlm/internlm2-math-base-20b ) |
153- | internlm2-math-20b-chat| [ Shanghai_AI_Laboratory/internlm2-math-20b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-math-20b/summary ) | wqkv| internlm2| ✔ ; | ✔ ; || math| [ internlm/internlm2-math-20b] ( https://huggingface.co/internlm/internlm2-math-20b ) |
139+ | internlm2-1_8b| [ Shanghai_AI_Laboratory/internlm2-1_8b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-1_8b/summary ) | wqkv| default-generation-bos| ✔ ; | ✔ ; | transformers>=4.35 | -| [ internlm/internlm2-1_8b] ( https://huggingface.co/internlm/internlm2-1_8b ) |
140+ | internlm2-1_8b-sft-chat| [ Shanghai_AI_Laboratory/internlm2-chat-1_8b-sft] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-1_8b-sft/summary ) | wqkv| internlm2| ✔ ; | ✔ ; | transformers>=4.35 | -| [ internlm/internlm2-chat-1_8b-sft] ( https://huggingface.co/internlm/internlm2-chat-1_8b-sft ) |
141+ | internlm2-1_8b-chat| [ Shanghai_AI_Laboratory/internlm2-chat-1_8b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-1_8b/summary ) | wqkv| internlm2| ✔ ; | ✔ ; | transformers>=4.35 | -| [ internlm/internlm2-chat-1_8b] ( https://huggingface.co/internlm/internlm2-chat-1_8b ) |
142+ | internlm2-7b-base| [ Shanghai_AI_Laboratory/internlm2-base-7b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-base-7b/summary ) | wqkv| default-generation-bos| ✔ ; | ✔ ; | transformers>=4.35 | -| [ internlm/internlm2-base-7b] ( https://huggingface.co/internlm/internlm2-base-7b ) |
143+ | internlm2-7b| [ Shanghai_AI_Laboratory/internlm2-7b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-7b/summary ) | wqkv| default-generation-bos| ✔ ; | ✔ ; | transformers>=4.35 | -| [ internlm/internlm2-7b] ( https://huggingface.co/internlm/internlm2-7b ) |
144+ | internlm2-7b-sft-chat| [ Shanghai_AI_Laboratory/internlm2-chat-7b-sft] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-7b-sft/summary ) | wqkv| internlm2| ✔ ; | ✔ ; | transformers>=4.35 | -| [ internlm/internlm2-chat-7b-sft] ( https://huggingface.co/internlm/internlm2-chat-7b-sft ) |
145+ | internlm2-7b-chat| [ Shanghai_AI_Laboratory/internlm2-chat-7b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-7b/summary ) | wqkv| internlm2| ✔ ; | ✔ ; | transformers>=4.35 | -| [ internlm/internlm2-chat-7b] ( https://huggingface.co/internlm/internlm2-chat-7b ) |
146+ | internlm2-20b-base| [ Shanghai_AI_Laboratory/internlm2-base-20b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-base-20b/summary ) | wqkv| default-generation-bos| ✔ ; | ✔ ; | transformers>=4.35 | -| [ internlm/internlm2-base-20b] ( https://huggingface.co/internlm/internlm2-base-20b ) |
147+ | internlm2-20b| [ Shanghai_AI_Laboratory/internlm2-20b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-20b/summary ) | wqkv| default-generation-bos| ✔ ; | ✔ ; | transformers>=4.35 | -| [ internlm/internlm2-20b] ( https://huggingface.co/internlm/internlm2-20b ) |
148+ | internlm2-20b-sft-chat| [ Shanghai_AI_Laboratory/internlm2-chat-20b-sft] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-20b-sft/summary ) | wqkv| internlm2| ✔ ; | ✔ ; | transformers>=4.35 | -| [ internlm/internlm2-chat-20b-sft] ( https://huggingface.co/internlm/internlm2-chat-20b-sft ) |
149+ | internlm2-20b-chat| [ Shanghai_AI_Laboratory/internlm2-chat-20b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-20b/summary ) | wqkv| internlm2| ✔ ; | ✔ ; | transformers>=4.35 | -| [ internlm/internlm2-chat-20b] ( https://huggingface.co/internlm/internlm2-chat-20b ) |
150+ | internlm2-math-7b| [ Shanghai_AI_Laboratory/internlm2-math-base-7b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-math-base-7b/summary ) | wqkv| default-generation-bos| ✔ ; | ✔ ; | transformers>=4.35 | math| [ internlm/internlm2-math-base-7b] ( https://huggingface.co/internlm/internlm2-math-base-7b ) |
151+ | internlm2-math-7b-chat| [ Shanghai_AI_Laboratory/internlm2-math-7b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-math-7b/summary ) | wqkv| internlm2| ✔ ; | ✔ ; | transformers>=4.35 | math| [ internlm/internlm2-math-7b] ( https://huggingface.co/internlm/internlm2-math-7b ) |
152+ | 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-bos| ✔ ; | ✔ ; | transformers>=4.35 | math| [ internlm/internlm2-math-base-20b] ( https://huggingface.co/internlm/internlm2-math-base-20b ) |
153+ | internlm2-math-20b-chat| [ Shanghai_AI_Laboratory/internlm2-math-20b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-math-20b/summary ) | wqkv| internlm2| ✔ ; | ✔ ; | transformers>=4.35 | math| [ internlm/internlm2-math-20b] ( https://huggingface.co/internlm/internlm2-math-20b ) |
154154| internlm-xcomposer2-7b-chat| [ Shanghai_AI_Laboratory/internlm-xcomposer2-7b] ( https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm-xcomposer2-7b/summary ) | wqkv| internlm-xcomposer2| ✔ ; | ✘ ; || multi-modal, vision| [ internlm/internlm-xcomposer2-7b] ( https://huggingface.co/internlm/internlm-xcomposer2-7b ) |
155155| 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-bos| ✔ ; | ✔ ; || -| [ deepseek-ai/deepseek-llm-7b-base] ( https://huggingface.co/deepseek-ai/deepseek-llm-7b-base ) |
156156| 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| ✔ ; | ✔ ; || -| [ deepseek-ai/deepseek-llm-7b-chat] ( https://huggingface.co/deepseek-ai/deepseek-llm-7b-chat ) |
0 commit comments