[Model] add minicpm (#3893)

README.md

@@ -70,6 +70,7 @@ vLLM seamlessly supports many Hugging Face models, including the following archi
 - InternLM2 (`internlm/internlm2-7b`, `internlm/internlm2-chat-7b`, etc.)
 - Jais (`core42/jais-13b`, `core42/jais-13b-chat`, `core42/jais-30b-v3`, `core42/jais-30b-chat-v3`, etc.)
 - LLaMA & LLaMA-2 (`meta-llama/Llama-2-70b-hf`, `lmsys/vicuna-13b-v1.3`, `young-geng/koala`, `openlm-research/open_llama_13b`, etc.)
+- MiniCPM (`openbmb/MiniCPM-2B-sft-bf16`, `openbmb/MiniCPM-2B-dpo-bf16`, etc.)
 - Mistral (`mistralai/Mistral-7B-v0.1`, `mistralai/Mistral-7B-Instruct-v0.1`, etc.)
 - Mixtral (`mistralai/Mixtral-8x7B-v0.1`, `mistralai/Mixtral-8x7B-Instruct-v0.1`, etc.)
 - MPT (`mosaicml/mpt-7b`, `mosaicml/mpt-30b`, etc.)

docs/source/models/supported_models.rst

@@ -83,6 +83,10 @@ Alongside each architecture, we include some popular models that use it.
     - LLaMA, LLaMA-2, Vicuna, Alpaca, Yi
     - :code:`meta-llama/Llama-2-13b-hf`, :code:`meta-llama/Llama-2-70b-hf`, :code:`openlm-research/open_llama_13b`, :code:`lmsys/vicuna-13b-v1.3`, :code:`01-ai/Yi-6B`, :code:`01-ai/Yi-34B`, etc.
     - ✅︎
+  * - :code:`MiniCPMForCausalLM`
+    - MiniCPM
+    - :code:`openbmb/MiniCPM-2B-sft-bf16`, :code:`openbmb/MiniCPM-2B-dpo-bf16`, etc.
+    -
   * - :code:`MistralForCausalLM`
     - Mistral, Mistral-Instruct
     - :code:`mistralai/Mistral-7B-v0.1`, :code:`mistralai/Mistral-7B-Instruct-v0.1`, etc.

vllm/model_executor/models/__init__.py

@@ -41,6 +41,7 @@ _MODELS = {
     # transformers's mpt class has lower case
     "MptForCausalLM": ("mpt", "MPTForCausalLM"),
     "MPTForCausalLM": ("mpt", "MPTForCausalLM"),
+    "MiniCPMForCausalLM": ("minicpm", "MiniCPMForCausalLM"),
     "OLMoForCausalLM": ("olmo", "OLMoForCausalLM"),
     "OPTForCausalLM": ("opt", "OPTForCausalLM"),
     "OrionForCausalLM": ("orion", "OrionForCausalLM"),