A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 17, 06:45 UTC
Add Mistral 7B to `test_models` (#1366)
Woosuk Kwon committed
Oct 16, 2023 at 17:49 UTC
95248677014cb10a9dbaa2e72f688e1a6e6cf566
1 file changed
+3
-2
tests/models/test_models.py
+3
-2
@@ -6,14 +6,15 @@ import pytest
6
7
MODELS = [
8
"facebook/opt-125m",
9
+ "meta-llama/Llama-2-7b-hf",
10
+ "mistralai/Mistral-7B-v0.1",
11
+ "tiiuae/falcon-7b",
12
"gpt2",
13
"bigcode/tiny_starcoder_py",
14
"EleutherAI/gpt-j-6b",
15
"EleutherAI/pythia-70m",
16
"bigscience/bloom-560m",
17
"mosaicml/mpt-7b",
15
- "tiiuae/falcon-7b",
16
- "meta-llama/Llama-2-7b-hf",
18
]
19
20