jiamingshan/AHA-L2A-Qwen3-1.7B-repro
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: jiamingshan/AHA-L2A-Qwen3-1.7B-repro
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-21 11:06:13 +08:00
commit c13d63b439
48 changed files with 165513 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
recipe/data/am_distilled_long_mix/build_summary.json Normal file
View File

@@ -0,0 +1,18 @@
{
"source_dataset": "/workspace/AHA/AHA-OLMO2/experiments/datasets/am-distilled-32768",
"output_dataset": "/workspace/AHA/AHA-Qwen3/experiments/datasets/am-distilled-32768-mix-long12k512-rand512",
"seed": 124,
"long_n": 512,
"rand_n": 512,
"min_long": 12288,
"rows": 1024,
"min_tokens": 369,
"p50": 12580,
"p90": 21189,
"p95": 24547,
"p99": 30902,
"max_tokens": 32618,
"mean_tokens": 10600.341796875,
"frac_ge_8192": 0.5517578125,
"frac_ge_12288": 0.5302734375
}

1
recipe/data/am_distilled_long_mix/dataset_dict.json Normal file
View File

@@ -0,0 +1 @@
{"splits": ["train"]}

3
recipe/data/am_distilled_long_mix/train/cache-e6708cbf54082730.arrow Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0135bf6e96f7a4f452894727b9be1ce92ff27cc65330b94faeab11e993f5aa3c
size 61801216

3
recipe/data/am_distilled_long_mix/train/data-00000-of-00001.arrow Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:27f158ba22512269d33e8fb14db97a84e541ca9b701fba73a98e70c73687f45c
size 87171000

152
recipe/data/am_distilled_long_mix/train/dataset_info.json Normal file
View File

@@ -0,0 +1,152 @@
{
"builder_name": "generator",
"citation": "",
"config_name": "default",
"dataset_name": "generator",
"dataset_size": 45895360821,
"description": "",
"download_checksums": {},
"download_size": 0,
"features": {
"messages": {
"feature": {
"content": {
"dtype": "string",
"_type": "Value"
},
"role": {
"dtype": "string",
"_type": "Value"
}
},
"_type": "List"
},
"input_ids": {
"feature": {
"dtype": "int32",
"_type": "Value"
},
"_type": "List"
},
"attention_mask": {
"feature": {
"dtype": "int8",
"_type": "Value"
},
"_type": "List"
},
"num_tokens": {
"dtype": "int64",
"_type": "Value"
}
},
"homepage": "",
"license": "",
"size_in_bytes": 45895360821,
"splits": {
"train": {
"name": "train",
"num_bytes": 45895360821,
"num_examples": 1890613,
"shard_lengths": [
15000,
14000,
14000,
14000,
14000,
14000,
14000,
15000,
14000,
14000,
14000,
14000,
14000,
14000,
14000,
14000,
14000,
14000,
14000,
14000,
14000,
14000,
14000,
25000,
26000,
27000,
26000,
26000,
25000,
26000,
25000,
26000,
25000,
26000,
25000,
26000,
26000,
25000,
25000,
25000,
24000,
25000,
24000,
24000,
24000,
24000,
23000,
19000,
18000,
18000,
18000,
18000,
18000,
18000,
18000,
19000,
22000,
23000,
23000,
23000,
23000,
23000,
23000,
23000,
23000,
23000,
23000,
22000,
22000,
23000,
22000,
22000,
22000,
23000,
22000,
22000,
22000,
22000,
23000,
23000,
23000,
23000,
22000,
22000,
28000,
30000,
30000,
29000,
30000,
20613
],
"dataset_name": "generator"
}
},
"version": {
"version_str": "0.0.0",
"major": 0,
"minor": 0,
"patch": 0
}
}

18
recipe/data/am_distilled_long_mix/train/state.json Normal file
View File

@@ -0,0 +1,18 @@
{
"_data_files": [
{
"filename": "data-00000-of-00001.arrow"
}
],
"_fingerprint": "8470c8174c1f6ae9",
"_format_columns": [
"attention_mask",
"input_ids",
"messages",
"num_tokens"
],
"_format_kwargs": {},
"_format_type": null,
"_output_all_columns": false,
"_split": null
}