@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 9524867701
Fork 0

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