Skip to content

Commit ab3a5a8

Browse files
authored
Support OLMo models. (#2832)
1 parent a61f052 commit ab3a5a8

File tree

7 files changed

+471
-5
lines changed

7 files changed

+471
-5
lines changed

README.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -70,6 +70,7 @@ vLLM seamlessly supports many Hugging Face models, including the following archi
7070
- Mistral (`mistralai/Mistral-7B-v0.1`, `mistralai/Mistral-7B-Instruct-v0.1`, etc.)
7171
- Mixtral (`mistralai/Mixtral-8x7B-v0.1`, `mistralai/Mixtral-8x7B-Instruct-v0.1`, etc.)
7272
- MPT (`mosaicml/mpt-7b`, `mosaicml/mpt-30b`, etc.)
73+
- OLMo (`allenai/OLMo-1B`, `allenai/OLMo-7B`, etc.)
7374
- OPT (`facebook/opt-66b`, `facebook/opt-iml-max-30b`, etc.)
7475
- Phi (`microsoft/phi-1_5`, `microsoft/phi-2`, etc.)
7576
- Qwen (`Qwen/Qwen-7B`, `Qwen/Qwen-7B-Chat`, etc.)

docs/source/models/supported_models.rst

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -62,6 +62,9 @@ Alongside each architecture, we include some popular models that use it.
6262
* - :code:`MPTForCausalLM`
6363
- MPT, MPT-Instruct, MPT-Chat, MPT-StoryWriter
6464
- :code:`mosaicml/mpt-7b`, :code:`mosaicml/mpt-7b-storywriter`, :code:`mosaicml/mpt-30b`, etc.
65+
* - :code:`OLMoForCausalLM`
66+
- OLMo
67+
- :code:`allenai/OLMo-1B`, :code:`allenai/OLMo-7B`, etc.
6568
* - :code:`OPTForCausalLM`
6669
- OPT, OPT-IML
6770
- :code:`facebook/opt-66b`, :code:`facebook/opt-iml-max-30b`, etc.

tests/models/test_models.py

Lines changed: 14 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -5,11 +5,20 @@
55
import pytest
66

77
MODELS = [
8-
"facebook/opt-125m", "meta-llama/Llama-2-7b-hf",
9-
"mistralai/Mistral-7B-v0.1", "Deci/DeciLM-7b", "tiiuae/falcon-7b", "gpt2",
10-
"bigcode/tiny_starcoder_py", "EleutherAI/gpt-j-6b",
11-
"EleutherAI/pythia-70m", "bigscience/bloom-560m", "mosaicml/mpt-7b",
12-
"microsoft/phi-2", "stabilityai/stablelm-3b-4e1t"
8+
"facebook/opt-125m",
9+
"meta-llama/Llama-2-7b-hf",
10+
"mistralai/Mistral-7B-v0.1",
11+
"Deci/DeciLM-7b",
12+
"tiiuae/falcon-7b",
13+
"gpt2",
14+
"bigcode/tiny_starcoder_py",
15+
"EleutherAI/gpt-j-6b",
16+
"EleutherAI/pythia-70m",
17+
"bigscience/bloom-560m",
18+
"mosaicml/mpt-7b",
19+
"microsoft/phi-2",
20+
"stabilityai/stablelm-3b-4e1t",
21+
"allenai/OLMo-1B",
1322
]
1423

1524

vllm/model_executor/models/__init__.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -35,6 +35,7 @@
3535
# transformers's mpt class has lower case
3636
"MptForCausalLM": ("mpt", "MPTForCausalLM"),
3737
"MPTForCausalLM": ("mpt", "MPTForCausalLM"),
38+
"OLMoForCausalLM": ("olmo", "OLMoForCausalLM"),
3839
"OPTForCausalLM": ("opt", "OPTForCausalLM"),
3940
"PhiForCausalLM": ("phi", "PhiForCausalLM"),
4041
"QWenLMHeadModel": ("qwen", "QWenLMHeadModel"),

0 commit comments

Comments
 (0)