82 lines
1.8 KiB
YAML
82 lines
1.8 KiB
YAML
cluster_args:
|
|
cluster_description: null
|
|
cluster_method: agglomerative
|
|
compression_ratio: 0.25
|
|
expert_sim: ttm
|
|
frequency_penalty: true
|
|
linkage_method: average
|
|
max_cluster_size: null
|
|
multi_layer: null
|
|
num_clusters: null
|
|
singleton_outlier_experts: false
|
|
singleton_super_experts: false
|
|
softmax_temperature: null
|
|
ds_args:
|
|
dataset_config_name: null
|
|
dataset_name: theblackcat102/evol-codealpaca-v1
|
|
dataset_test_split: test
|
|
shuffle: true
|
|
split: train
|
|
eval_args:
|
|
evalplus_tasks:
|
|
- mbpp
|
|
- humaneval
|
|
greedy: true
|
|
lm_eval_tasks:
|
|
- winogrande
|
|
- arc_challenge
|
|
- arc_easy
|
|
- boolq
|
|
- hellaswag
|
|
- mmlu
|
|
- openbookqa
|
|
- rte
|
|
min_p: 0.0
|
|
parallel_tasks: 32
|
|
results_dir: null
|
|
run_evalplus: true
|
|
run_livecodebench: true
|
|
run_lm_eval: true
|
|
run_math: false
|
|
run_wildbench: false
|
|
server_log_file_name: server.log
|
|
temperature: 0.7
|
|
top_k: 20
|
|
top_p: 0.8
|
|
use_server: true
|
|
vllm_port: 8000
|
|
layerwise_args:
|
|
batch_group_size: 8
|
|
low_cpu_mem_usage: true
|
|
save_intermediate: false
|
|
model_args:
|
|
model_name: ATH-MaaS/Marco-Nano-Instruct
|
|
num_experts_per_tok_override: null
|
|
obs_args:
|
|
batch_size: 1
|
|
batches_per_category: 128
|
|
distance_measure: angular
|
|
model_max_length: 2048
|
|
output_file_name: observations_marco_128x2048_reap.pt
|
|
overwrite_observations: false
|
|
record_pruning_metrics_only: true
|
|
renormalize_router_weights: true
|
|
return_vllm_tokens_prompt: false
|
|
select_only_categories: null
|
|
split_by_category: false
|
|
truncate: false
|
|
prune_args:
|
|
n_experts_to_prune: null
|
|
overwrite_pruned_model: true
|
|
perserve_outliers: false
|
|
perserve_super_experts: false
|
|
prune_method: reap
|
|
reap_args:
|
|
debug: false
|
|
do_eval: false
|
|
plot_clusters: true
|
|
profile: false
|
|
run_observer_only: false
|
|
seed: 42
|
|
smoke_test: false
|