namkoong-lab/LatentGym_Qwen3-8B_10episodes_MultiLatent_number_guessing
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: namkoong-lab/LatentGym_Qwen3-8B_10episodes_MultiLatent_number_guessing
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-17 13:07:51 +08:00
commit fe6e9c4862
17 changed files with 152416 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

56
_provenance.json Normal file
View File

@@ -0,0 +1,56 @@
{
"base_model": "Qwen/Qwen3-8B",
"copied_at": "2026-06-08T16:48:27.766023Z",
"eval_envs": [
"number_guessing"
],
"held_out_envs": [],
"mode_prefix": "10episodes",
"n_episodes": 10,
"new_name": "LatentGym_Qwen3-8B_10episodes_MultiLatent_number_guessing_best",
"scope_key": "MultiLatent_number_guessing",
"sha256": {
"added_tokens.json": "c0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680",
"chat_template.jinja": "a55ee1b1660128b7098723e0abcd92caa0788061051c62d51cbe87d9cf1974d8",
"config.json": "38a8a5a58ef8dfdfe121758e5ed011e66d9e46f42c4dde7b0ed4d111f0596775",
"generation_config.json": "64d86df2173901c58389974bde21f7d2ab9eb7d79f35a337753329d39cf265c0",
"merges.txt": "8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5",
"model-00001-of-00004.safetensors": "9b570a4560b139dee5cf70d304154ce5188a1d5b8b21662d4a7912a45a3c2972",
"model-00002-of-00004.safetensors": "f5574bed2552cd3e8cc3bcdf6a7ab44cf23b7b98243a7db7b195fd5ab0d835b5",
"model-00003-of-00004.safetensors": "a33421c0d85104ae59ae1a45f6e9118766ea6eb098d2ba0658ae5c4c90a55d86",
"model-00004-of-00004.safetensors": "00abb9608e188c95236712d05958dc34b4073f200aa493037259226099f21ae3",
"model.safetensors.index.json": "e7e4bdc58d3302c97357f27979b270987dd620cf0cd9b1c130e3a51c9d64df95",
"special_tokens_map.json": "76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd",
"tokenizer_config.json": "443bfa629eb16387a12edbf92a76f6a6f10b2af3b53d87ba1550adfcf45f7fa0"
},
"shards": [
"model-00001-of-00004.safetensors",
"model-00002-of-00004.safetensors",
"model-00003-of-00004.safetensors",
"model-00004-of-00004.safetensors"
],
"small_files": [
"config.json",
"generation_config.json",
"tokenizer_config.json",
"special_tokens_map.json",
"added_tokens.json",
"chat_template.jinja",
"merges.txt",
"model.safetensors.index.json"
],
"source_hydra_config_path": "/pscratch/sd/n/nye1030/TrainExplore/V1_3Lats/Qwen3-8B_v1_ng_3lats_ne=10_tbs=32_nsp=8_mbs=16_plr=5e-07_kl=0.04_seed=263/hydra/.hydra/config.yaml",
"source_job_dir": "/pscratch/sd/n/nye1030/TrainExplore/V1_3Lats/Qwen3-8B_v1_ng_3lats_ne=10_tbs=32_nsp=8_mbs=16_plr=5e-07_kl=0.04_seed=263",
"source_step": "global_step_562",
"train_envs": [
"number_guessing"
],
"trained_latents": {
"number_guessing": [
"set_of_2",
"set_of_3",
"dynamic_range"
]
},
"variant": "best"
}