Skip to content

Commit 9568450

Browse files
committed
update folder and files based on discussions
1 parent 83d644d commit 9568450

File tree

5 files changed

+45
-48
lines changed

5 files changed

+45
-48
lines changed

README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2,4 +2,4 @@
22

33
This repository contains configurations for model validation.
44

5-
The `lm-eval` folder contains YAML files for each model that configures information needed for the model to be validated through the [lm-evaluation-harness](https://github.com/huggingface/lm-evaluation-harness).
5+
The `accuracy` folder contains YAML files for each model that configures information needed for the model to be validated through the [llm-eval-test](https://github.com/openshift-psap/llm-eval-test)
Lines changed: 35 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,35 @@
1+
# accuracy configs for https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct
2+
model: "vllm"
3+
model_args:
4+
pretrained: "meta-llama/Meta-Llama-3.1-8B-Instruct"
5+
num_fewshot:
6+
apply_chat_template: true
7+
fewshot_as_multiturn: true
8+
add_bos_token: false
9+
tasks:
10+
- name: "leaderboard_bbh"
11+
metrics:
12+
- name: "acc_norm,none"
13+
value: 0.50946
14+
- name: "leaderboard_gpqa"
15+
metrics:
16+
- name: "acc_norm,none"
17+
value: 0.29698
18+
- name: "leaderboard_ifeval"
19+
metrics:
20+
- name: "inst_level_loose_acc,none"
21+
value: 0.85851
22+
- name: "inst_level_strict_acc,none"
23+
value: 0.82374
24+
- name: "prompt_level_loose_acc,none"
25+
value: 0.79667
26+
- name: "prompt_level_strict_acc,none"
27+
value: 0.74861
28+
- name: "leaderboard_math_hard"
29+
metrics:
30+
- name: "exact_match,none"
31+
value: 0.19864
32+
- name: "leaderboard_musr"
33+
metrics:
34+
- name: "acc_norm,none"
35+
value: 0.38359
Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
# storage configs for https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct
2+
model: hf
3+
data: hf
Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,6 @@
1+
# server configs for https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct
2+
model: "meta-llama/Meta-Llama-3.1-8B-Instruct"
3+
trust_remote_code: true
4+
enable_chunked_prefill: true
5+
tensor_parallel_size:
6+
max_model_len: 4096

lm-eval/Meta-Llama-3.1-8B-Instruct.yaml

Lines changed: 0 additions & 47 deletions
This file was deleted.

0 commit comments

Comments
 (0)