add internlm3-dense(turbomind) & chat template

lmdeploy/model.py

@@ -443,11 +443,12 @@ def match(cls, model_path: str) -> Optional[str]:
             model_path (str): the model path used for matching.
         """
         path = model_path.lower()
-        if all([c not in path for c in ['internlm2', '8k']]) and \
+        if all([c not in path for c in ['internlm3', 'internlm2', '8k']]) and \
                 all([c in path for c in ['internlm', 'chat']]):
             return 'internlm'
 
 
+@MODELS.register_module(name='internlm3')
 @MODELS.register_module(name='internlm2')
 class InternLM2Chat7B(InternLMChat7B):
     """Chat template and generation parameters of InternLM2-Chat-7B."""
@@ -490,6 +491,8 @@ def match(cls, model_path: str) -> Optional[str]:
         path = model_path.lower()
         if 'internlm2' in path and ('chat' in path or 'math' in path):
             return 'internlm2'
+        if 'internlm3' in path and ('chat' in path or 'math' in path):
+            return 'internlm3'
 
     def messages2prompt(self,
                         messages,

lmdeploy/turbomind/deploy/source_model/llama.py

@@ -191,7 +191,7 @@ def model_info(self):
 
         return dict(
             size_per_head=head_dim,
-            rotary_embedding=hidden_units // attn_head_num,
+            rotary_embedding=head_dim,
             num_layer=num_layer,
             norm_eps=norm_eps,
             head_num=attn_head_num,

lmdeploy/turbomind/supported_models.py

@@ -13,6 +13,8 @@
     InternLMForCausalLM='llama',
     # internlm2
     InternLM2ForCausalLM='internlm2',
+    # internlm3
+    InternLM3ForCausalLM='llama',
     # llama, llama2, alpaca, vicuna, codellama, ultracm, yi,
     # deepseek-coder, deepseek-llm
     LlamaForCausalLM='llama',