[CI] Prune down lm-eval small tests (#17012)

Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin 2025-05-08 15:00:26 -04:00 committed by GitHub
parent a83a0f92b5
commit 8342e3abd1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 36 additions and 6 deletions

View File

@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m RedHatAI/Llama-3.2-1B-Instruct-FP8 -b "auto" -l 1319 -f 5 -t 1
model_name: "RedHatAI/Llama-3.2-1B-Instruct-FP8"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.335
- name: "exact_match,flexible-extract"
value: 0.323
limit: 1319
num_fewshot: 5

View File

@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m Qwen/Qwen2.5-1.5B-Instruct -b auto -l 1319 -f 5 -t 1
model_name: "Qwen/Qwen2.5-1.5B-Instruct"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.54
- name: "exact_match,flexible-extract"
value: 0.59
limit: 1319
num_fewshot: 5

View File

@ -0,0 +1,11 @@
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m RedHatAI/Qwen2.5-VL-3B-Instruct-FP8-Dynamic -b auto -l 1319 -f 5 -t 1
model_name: "RedHatAI/Qwen2.5-VL-3B-Instruct-FP8-Dynamic"
tasks:
- name: "gsm8k"
metrics:
- name: "exact_match,strict-match"
value: 0.47
- name: "exact_match,flexible-extract"
value: 0.64
limit: 1319
num_fewshot: 5

View File

@ -3,3 +3,4 @@ Meta-Llama-3-70B-Instruct.yaml
Mixtral-8x7B-Instruct-v0.1.yaml
Qwen2-57B-A14-Instruct.yaml
DeepSeek-V2-Lite-Chat.yaml
Meta-Llama-3-8B-QQQ.yaml

View File

@ -1,10 +1,6 @@
Meta-Llama-3-8B-Instruct.yaml
Meta-Llama-3-8B-Instruct-FP8-compressed-tensors.yaml
Qwen2.5-1.5B-Instruct.yaml
Meta-Llama-3.2-1B-Instruct-INT8-compressed-tensors.yaml
Meta-Llama-3-8B-Instruct-INT8-compressed-tensors-asym.yaml
Meta-Llama-3-8B-Instruct-nonuniform-compressed-tensors.yaml
Meta-Llama-3-8B-Instruct-Channelwise-compressed-tensors.yaml
Qwen2.5-VL-3B-Instruct-FP8-dynamic.yaml
Qwen1.5-MoE-W4A16-compressed-tensors.yaml
Qwen2-1.5B-Instruct-INT8-compressed-tensors.yaml
Qwen2-1.5B-Instruct-FP8W8.yaml
Meta-Llama-3-8B-QQQ.yaml