Skip to page content
SAVRN
Search Plan a project

Open-weight model

iii-rlfix-qwen3-8b

by Jord Nguyen Jordine/iii-rlfix-qwen3-8b

iii-rlfix-qwen3-8b is an open-weight model from Jord Nguyen. Its published files total 32.1 GB.

Parameters—
Context—
Weights32.1 GB
License—
AccessOpen weights
Monthly Downloads—

Model Card

The publisher has not written a card for this model.

Identity and Version

Repository
Jordine/iii-rlfix-qwen3-8b
Publisher
Jord Nguyen
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
133fa4e79952ff779da322e20f81600551f93335
First published
2026-10-13
Last updated
2026-10-14

Files and Weights

1,237 files, 32.1 GB in total. The weights are 367 files totalling 32.1 GB in safetensors.

Weights367 files · 32.1 GB
Configuration454 files · 4.5 MB
Documentation367 files · 1.9 MB
Other48 files · 4.1 MB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
dpo/adapter_final/adapter_model.safetensorsWeights87.4 MB bae46e75d751
dpo/adapter_step100/adapter_model.safetensorsWeights87.4 MB cf1b46dfa6da
dpo/adapter_step1000/adapter_model.safetensorsWeights87.4 MB a8d0d6b08891
dpo/adapter_step1050/adapter_model.safetensorsWeights87.4 MB b4404181e758
dpo/adapter_step1100/adapter_model.safetensorsWeights87.4 MB 6154b523d357
dpo/adapter_step1150/adapter_model.safetensorsWeights87.4 MB 0e4911a601f7
dpo/adapter_step1200/adapter_model.safetensorsWeights87.4 MB d5044c16f6dd
dpo/adapter_step1250/adapter_model.safetensorsWeights87.4 MB 6c7349eaaf87
dpo/adapter_step1300/adapter_model.safetensorsWeights87.4 MB c53c288ca7c0
dpo/adapter_step1350/adapter_model.safetensorsWeights87.4 MB e1cfe043a196
dpo/adapter_step1400/adapter_model.safetensorsWeights87.4 MB cba23148921f
dpo/adapter_step1450/adapter_model.safetensorsWeights87.4 MB 5b1a1ecc119a
dpo/adapter_step150/adapter_model.safetensorsWeights87.4 MB 2df79384471d
dpo/adapter_step1500/adapter_model.safetensorsWeights87.4 MB bae46e75d751
dpo/adapter_step200/adapter_model.safetensorsWeights87.4 MB aca1ee56f288
dpo/adapter_step250/adapter_model.safetensorsWeights87.4 MB b98333901939
dpo/adapter_step300/adapter_model.safetensorsWeights87.4 MB be6263063e6a
dpo/adapter_step350/adapter_model.safetensorsWeights87.4 MB 8546689f0c12
dpo/adapter_step400/adapter_model.safetensorsWeights87.4 MB 517f7cca9a22
dpo/adapter_step450/adapter_model.safetensorsWeights87.4 MB 05f0a229fbb1
dpo/adapter_step50/adapter_model.safetensorsWeights87.4 MB c1e31e2a6176
dpo/adapter_step500/adapter_model.safetensorsWeights87.4 MB af562682db2e
dpo/adapter_step550/adapter_model.safetensorsWeights87.4 MB f4a8d65ae0c6
dpo/adapter_step600/adapter_model.safetensorsWeights87.4 MB 99072da712d3
dpo/adapter_step650/adapter_model.safetensorsWeights87.4 MB 95a560e66a3e
dpo/adapter_step700/adapter_model.safetensorsWeights87.4 MB 00578eaa1402
dpo/adapter_step750/adapter_model.safetensorsWeights87.4 MB c6adf88489a6
dpo/adapter_step800/adapter_model.safetensorsWeights87.4 MB 3103f194671f
dpo/adapter_step850/adapter_model.safetensorsWeights87.4 MB 021b4246d2ed
dpo/adapter_step900/adapter_model.safetensorsWeights87.4 MB f8a677ae6081
dpo/adapter_step950/adapter_model.safetensorsWeights87.4 MB 80bff651b475
rl_exact_ent/adapter_step100/adapter_model.safetensorsWeights87.4 MB 01febb4a06fe
rl_exact_ent/adapter_step150/adapter_model.safetensorsWeights87.4 MB d1b5e29745b6
rl_exact_ent/adapter_step200/adapter_model.safetensorsWeights87.4 MB 5e7b02397688
rl_exact_ent/adapter_step250/adapter_model.safetensorsWeights87.4 MB 24d761ec62b5
rl_exact_ent/adapter_step300/adapter_model.safetensorsWeights87.4 MB e0f5f897cdcc
rl_exact_ent/adapter_step350/adapter_model.safetensorsWeights87.4 MB f51280b1abbd
rl_exact_ent/adapter_step400/adapter_model.safetensorsWeights87.4 MB e8c18c40ed38
rl_exact_ent/adapter_step450/adapter_model.safetensorsWeights87.4 MB 5d966dcf58b5
rl_exact_ent/adapter_step50/adapter_model.safetensorsWeights87.4 MB efec78cd4901
rl_exact_ent/adapter_step500/adapter_model.safetensorsWeights87.4 MB 874ec0050380
rl_exact_ent/adapter_step550/adapter_model.safetensorsWeights87.4 MB 32659879eff4
rl_exact_ent/adapter_step600/adapter_model.safetensorsWeights87.4 MB 859885b5b985
rl_exact_ent/adapter_step650/adapter_model.safetensorsWeights87.4 MB 7a492410e113
rl_exact_ent/adapter_step700/adapter_model.safetensorsWeights87.4 MB 7c780cff9853
rl_exact_ent/adapter_step750/adapter_model.safetensorsWeights87.4 MB ef4af94c552f
rl_exact_ent/adapter_step800/adapter_model.safetensorsWeights87.4 MB 827e71cd98df
rl_exact_ent/adapter_step850/adapter_model.safetensorsWeights87.4 MB 1c67a58eaa59
rl_exact_ent/adapter_step900/adapter_model.safetensorsWeights87.4 MB e843dc944e9d
rl_exact_ent/adapter_step950/adapter_model.safetensorsWeights87.4 MB 6fb6cd3dfb36
rl_exact_lr2e5/adapter_final/adapter_model.safetensorsWeights87.4 MB 4028e249e167
rl_exact_lr2e5/adapter_step100/adapter_model.safetensorsWeights87.4 MB 1b07b6a65c56
rl_exact_lr2e5/adapter_step1000/adapter_model.safetensorsWeights87.4 MB d1f31fc4f16a
rl_exact_lr2e5/adapter_step1050/adapter_model.safetensorsWeights87.4 MB 2abad7cb5d9a
rl_exact_lr2e5/adapter_step1100/adapter_model.safetensorsWeights87.4 MB ae15a21ce8af
rl_exact_lr2e5/adapter_step1150/adapter_model.safetensorsWeights87.4 MB a87c7e733083
rl_exact_lr2e5/adapter_step1200/adapter_model.safetensorsWeights87.4 MB f4c4af38bcfa
rl_exact_lr2e5/adapter_step1250/adapter_model.safetensorsWeights87.4 MB cad15c0215ed
rl_exact_lr2e5/adapter_step1300/adapter_model.safetensorsWeights87.4 MB 717f39bf8bed
rl_exact_lr2e5/adapter_step1350/adapter_model.safetensorsWeights87.4 MB fb6560b588c7
rl_exact_lr2e5/adapter_step1400/adapter_model.safetensorsWeights87.4 MB 4be59ffec24f
rl_exact_lr2e5/adapter_step1450/adapter_model.safetensorsWeights87.4 MB fc407d70482f
rl_exact_lr2e5/adapter_step150/adapter_model.safetensorsWeights87.4 MB 74e3111b19c1
rl_exact_lr2e5/adapter_step1500/adapter_model.safetensorsWeights87.4 MB 4028e249e167
rl_exact_lr2e5/adapter_step200/adapter_model.safetensorsWeights87.4 MB f2c2cdcd81ad
rl_exact_lr2e5/adapter_step250/adapter_model.safetensorsWeights87.4 MB 2ffd303d0cbe
rl_exact_lr2e5/adapter_step300/adapter_model.safetensorsWeights87.4 MB 4dd852a9c5d3
rl_exact_lr2e5/adapter_step350/adapter_model.safetensorsWeights87.4 MB dda3a7ac8f6a
rl_exact_lr2e5/adapter_step400/adapter_model.safetensorsWeights87.4 MB 1b1bdaca4f3c
rl_exact_lr2e5/adapter_step450/adapter_model.safetensorsWeights87.4 MB a68a473d8a9e
rl_exact_lr2e5/adapter_step50/adapter_model.safetensorsWeights87.4 MB 3399b81f2e04
rl_exact_lr2e5/adapter_step500/adapter_model.safetensorsWeights87.4 MB c024b5f380b5
rl_exact_lr2e5/adapter_step550/adapter_model.safetensorsWeights87.4 MB a6c31c522036
rl_exact_lr2e5/adapter_step600/adapter_model.safetensorsWeights87.4 MB 7a15708e2ee2
rl_exact_lr2e5/adapter_step650/adapter_model.safetensorsWeights87.4 MB 4c66584ae4ab
rl_exact_lr2e5/adapter_step700/adapter_model.safetensorsWeights87.4 MB dde230774573
rl_exact_lr2e5/adapter_step750/adapter_model.safetensorsWeights87.4 MB 1b95f53a82d2
rl_exact_lr2e5/adapter_step800/adapter_model.safetensorsWeights87.4 MB ea5a3662328b
rl_exact_lr2e5/adapter_step850/adapter_model.safetensorsWeights87.4 MB 91d4f1eeb958
rl_exact_lr2e5/adapter_step900/adapter_model.safetensorsWeights87.4 MB 6698b3026537
rl_exact_lr2e5/adapter_step950/adapter_model.safetensorsWeights87.4 MB 049e2b66fc46
rl_exact_lr2e5_cont/adapter_final/adapter_model.safetensorsWeights87.4 MB a9b98598cc42
rl_exact_lr2e5_cont/adapter_step1550/adapter_model.safetensorsWeights87.4 MB d42dad6b9986
rl_exact_lr2e5_cont/adapter_step1600/adapter_model.safetensorsWeights87.4 MB 85ecbe9a7e5f
rl_exact_lr2e5_cont/adapter_step1650/adapter_model.safetensorsWeights87.4 MB ecb0bb887162
rl_exact_lr2e5_cont/adapter_step1700/adapter_model.safetensorsWeights87.4 MB 10c3d371cf88
rl_exact_lr2e5_cont/adapter_step1750/adapter_model.safetensorsWeights87.4 MB 94955b8f4662
rl_exact_lr2e5_cont/adapter_step1800/adapter_model.safetensorsWeights87.4 MB d8320804971f
rl_exact_lr2e5_cont/adapter_step1850/adapter_model.safetensorsWeights87.4 MB d16ad696570b
rl_exact_lr2e5_cont/adapter_step1900/adapter_model.safetensorsWeights87.4 MB ac23fa2f75f8
rl_exact_lr2e5_cont/adapter_step1950/adapter_model.safetensorsWeights87.4 MB f325b96a1995
rl_exact_lr2e5_cont/adapter_step2000/adapter_model.safetensorsWeights87.4 MB bbb5baf878a1
rl_exact_lr2e5_cont/adapter_step2050/adapter_model.safetensorsWeights87.4 MB 5ac153ae3c8d
rl_exact_lr2e5_cont/adapter_step2100/adapter_model.safetensorsWeights87.4 MB bd7ea1620196
rl_exact_lr2e5_cont/adapter_step2150/adapter_model.safetensorsWeights87.4 MB 5171c57ff18e
rl_exact_lr2e5_cont/adapter_step2200/adapter_model.safetensorsWeights87.4 MB a3639d9faff3
rl_exact_lr2e5_cont/adapter_step2250/adapter_model.safetensorsWeights87.4 MB b7de422d32bf
rl_exact_lr2e5_cont/adapter_step2300/adapter_model.safetensorsWeights87.4 MB 137945d071bb
rl_exact_lr2e5_cont/adapter_step2350/adapter_model.safetensorsWeights87.4 MB ba9967170cb0
rl_exact_lr2e5_cont/adapter_step2400/adapter_model.safetensorsWeights87.4 MB 63108ca3c4b1
rl_exact_lr2e5_cont/adapter_step2450/adapter_model.safetensorsWeights87.4 MB c77c847c9d9b
rl_exact_lr2e5_cont/adapter_step2500/adapter_model.safetensorsWeights87.4 MB cf3feb3682fe
rl_exact_lr2e5_cont/adapter_step2550/adapter_model.safetensorsWeights87.4 MB 64172b101a34
rl_exact_lr2e5_cont/adapter_step2600/adapter_model.safetensorsWeights87.4 MB c3647ccafcfb
rl_exact_lr2e5_cont/adapter_step2650/adapter_model.safetensorsWeights87.4 MB 5fb185f9fbcb
rl_exact_lr2e5_cont/adapter_step2700/adapter_model.safetensorsWeights87.4 MB ce26b8fbb095
rl_exact_lr2e5_cont/adapter_step2750/adapter_model.safetensorsWeights87.4 MB a42f2aa8f984
rl_exact_lr2e5_cont/adapter_step2800/adapter_model.safetensorsWeights87.4 MB c51b74341b56
rl_exact_lr2e5_cont/adapter_step2850/adapter_model.safetensorsWeights87.4 MB adbf91b08342
rl_exact_lr2e5_cont/adapter_step2900/adapter_model.safetensorsWeights87.4 MB 4c0ee2c93bce
rl_exact_lr2e5_cont/adapter_step2950/adapter_model.safetensorsWeights87.4 MB 731be9edafed
rl_exact_lr2e5_cont/adapter_step3000/adapter_model.safetensorsWeights87.4 MB a9b98598cc42
rl_exact_lr2e5_s7/adapter_step100/adapter_model.safetensorsWeights87.4 MB 4b3a46aaf985
rl_exact_lr2e5_s7/adapter_step1000/adapter_model.safetensorsWeights87.4 MB 1a6ffd72da60
rl_exact_lr2e5_s7/adapter_step1050/adapter_model.safetensorsWeights87.4 MB 407a8f5ec69f
rl_exact_lr2e5_s7/adapter_step1100/adapter_model.safetensorsWeights87.4 MB 452447aff3d7
rl_exact_lr2e5_s7/adapter_step1150/adapter_model.safetensorsWeights87.4 MB 9a8d567bf2b5
rl_exact_lr2e5_s7/adapter_step1200/adapter_model.safetensorsWeights87.4 MB cfccec725318
rl_exact_lr2e5_s7/adapter_step1250/adapter_model.safetensorsWeights87.4 MB 2ab9824c6c5d
rl_exact_lr2e5_s7/adapter_step1300/adapter_model.safetensorsWeights87.4 MB e9e708d5d3a4
rl_exact_lr2e5_s7/adapter_step1350/adapter_model.safetensorsWeights87.4 MB 2b78f71ebffc
rl_exact_lr2e5_s7/adapter_step1400/adapter_model.safetensorsWeights87.4 MB f8f67dde5677
rl_exact_lr2e5_s7/adapter_step1450/adapter_model.safetensorsWeights87.4 MB 40c32b22ed55
rl_exact_lr2e5_s7/adapter_step150/adapter_model.safetensorsWeights87.4 MB a56cebe53bd4
rl_exact_lr2e5_s7/adapter_step1500/adapter_model.safetensorsWeights87.4 MB ee381c6de779
rl_exact_lr2e5_s7/adapter_step1550/adapter_model.safetensorsWeights87.4 MB 93deda032f7a
rl_exact_lr2e5_s7/adapter_step1600/adapter_model.safetensorsWeights87.4 MB 7317bb318f32
rl_exact_lr2e5_s7/adapter_step1650/adapter_model.safetensorsWeights87.4 MB 6a6f48812c0a
rl_exact_lr2e5_s7/adapter_step1700/adapter_model.safetensorsWeights87.4 MB a76b47303373
rl_exact_lr2e5_s7/adapter_step1750/adapter_model.safetensorsWeights87.4 MB 0d229fa81367
rl_exact_lr2e5_s7/adapter_step1800/adapter_model.safetensorsWeights87.4 MB 6a75bba809b5
rl_exact_lr2e5_s7/adapter_step1850/adapter_model.safetensorsWeights87.4 MB 5ce74c5d6cad
rl_exact_lr2e5_s7/adapter_step1900/adapter_model.safetensorsWeights87.4 MB 61b44f8f862c
rl_exact_lr2e5_s7/adapter_step1950/adapter_model.safetensorsWeights87.4 MB 6851bd585b24
rl_exact_lr2e5_s7/adapter_step200/adapter_model.safetensorsWeights87.4 MB b93b39cffe30
rl_exact_lr2e5_s7/adapter_step250/adapter_model.safetensorsWeights87.4 MB ea4db3d06f97
rl_exact_lr2e5_s7/adapter_step300/adapter_model.safetensorsWeights87.4 MB 41266eabfe08
rl_exact_lr2e5_s7/adapter_step350/adapter_model.safetensorsWeights87.4 MB 084f0346d7b7
rl_exact_lr2e5_s7/adapter_step400/adapter_model.safetensorsWeights87.4 MB 8b8dab214924
rl_exact_lr2e5_s7/adapter_step450/adapter_model.safetensorsWeights87.4 MB 749dc2d07f91
rl_exact_lr2e5_s7/adapter_step50/adapter_model.safetensorsWeights87.4 MB 4425c8f984a5
rl_exact_lr2e5_s7/adapter_step500/adapter_model.safetensorsWeights87.4 MB 62a047ae0a7c
rl_exact_lr2e5_s7/adapter_step550/adapter_model.safetensorsWeights87.4 MB 7c61f1fa5b5c
rl_exact_lr2e5_s7/adapter_step600/adapter_model.safetensorsWeights87.4 MB 1c7d338f6795
rl_exact_lr2e5_s7/adapter_step650/adapter_model.safetensorsWeights87.4 MB a95a4936ff92
rl_exact_lr2e5_s7/adapter_step700/adapter_model.safetensorsWeights87.4 MB 10d4a9505d64
rl_exact_lr2e5_s7/adapter_step750/adapter_model.safetensorsWeights87.4 MB be6e46bf0f5f
rl_exact_lr2e5_s7/adapter_step800/adapter_model.safetensorsWeights87.4 MB f375d29cd560
rl_exact_lr2e5_s7/adapter_step850/adapter_model.safetensorsWeights87.4 MB 437c27253b90
rl_exact_lr2e5_s7/adapter_step900/adapter_model.safetensorsWeights87.4 MB b8b82d2ab404
rl_exact_lr2e5_s7/adapter_step950/adapter_model.safetensorsWeights87.4 MB 1dee2e21e2c6
rl_norm_lr2e5/adapter_final/adapter_model.safetensorsWeights87.4 MB bb6add238c6c
rl_norm_lr2e5/adapter_step100/adapter_model.safetensorsWeights87.4 MB 12f0beabf2cd
rl_norm_lr2e5/adapter_step1000/adapter_model.safetensorsWeights87.4 MB 44d86a4d83cf
rl_norm_lr2e5/adapter_step1050/adapter_model.safetensorsWeights87.4 MB f5d1498e080d
rl_norm_lr2e5/adapter_step1100/adapter_model.safetensorsWeights87.4 MB 8e7c936ff28c
rl_norm_lr2e5/adapter_step1150/adapter_model.safetensorsWeights87.4 MB f2493be0b24c
rl_norm_lr2e5/adapter_step1200/adapter_model.safetensorsWeights87.4 MB e838523de300
rl_norm_lr2e5/adapter_step1250/adapter_model.safetensorsWeights87.4 MB 62a5419dc737
rl_norm_lr2e5/adapter_step1300/adapter_model.safetensorsWeights87.4 MB 1fb235d3511f
rl_norm_lr2e5/adapter_step1350/adapter_model.safetensorsWeights87.4 MB 9a672129a6ec
rl_norm_lr2e5/adapter_step1400/adapter_model.safetensorsWeights87.4 MB 703faa1ddd3a
rl_norm_lr2e5/adapter_step1450/adapter_model.safetensorsWeights87.4 MB 0f86dd0f91c4
rl_norm_lr2e5/adapter_step150/adapter_model.safetensorsWeights87.4 MB bd05dffa648b
rl_norm_lr2e5/adapter_step1500/adapter_model.safetensorsWeights87.4 MB bb6add238c6c
rl_norm_lr2e5/adapter_step200/adapter_model.safetensorsWeights87.4 MB aa947b4769cc
rl_norm_lr2e5/adapter_step250/adapter_model.safetensorsWeights87.4 MB ece34ca71222
rl_norm_lr2e5/adapter_step300/adapter_model.safetensorsWeights87.4 MB 6aba67880c9d
rl_norm_lr2e5/adapter_step350/adapter_model.safetensorsWeights87.4 MB 680c9f9d92fb
rl_norm_lr2e5/adapter_step400/adapter_model.safetensorsWeights87.4 MB 076cd9779140
rl_norm_lr2e5/adapter_step450/adapter_model.safetensorsWeights87.4 MB 4bf774db85eb
rl_norm_lr2e5/adapter_step50/adapter_model.safetensorsWeights87.4 MB 6a000826b8ae
rl_norm_lr2e5/adapter_step500/adapter_model.safetensorsWeights87.4 MB 52179b79c35c
rl_norm_lr2e5/adapter_step550/adapter_model.safetensorsWeights87.4 MB 210ed42763e2
rl_norm_lr2e5/adapter_step600/adapter_model.safetensorsWeights87.4 MB ee9deae01149
rl_norm_lr2e5/adapter_step650/adapter_model.safetensorsWeights87.4 MB d67437eae1d6
rl_norm_lr2e5/adapter_step700/adapter_model.safetensorsWeights87.4 MB adc5017e529a
rl_norm_lr2e5/adapter_step750/adapter_model.safetensorsWeights87.4 MB aca2c6c8a7a5
rl_norm_lr2e5/adapter_step800/adapter_model.safetensorsWeights87.4 MB 9b216ce07dc9
rl_norm_lr2e5/adapter_step850/adapter_model.safetensorsWeights87.4 MB 0aa534e2710b
rl_norm_lr2e5/adapter_step900/adapter_model.safetensorsWeights87.4 MB 36dfb909c9d9
rl_norm_lr2e5/adapter_step950/adapter_model.safetensorsWeights87.4 MB dde3b4eda67f
rl_sample_loo/adapter_step100/adapter_model.safetensorsWeights87.4 MB 829453c8cef2
rl_sample_loo/adapter_step150/adapter_model.safetensorsWeights87.4 MB 6f2ea6b5f445
rl_sample_loo/adapter_step200/adapter_model.safetensorsWeights87.4 MB aa83cfb9dd27
rl_sample_loo/adapter_step250/adapter_model.safetensorsWeights87.4 MB c65069d999f7
rl_sample_loo/adapter_step300/adapter_model.safetensorsWeights87.4 MB 0d3dadf179b7
rl_sample_loo/adapter_step350/adapter_model.safetensorsWeights87.4 MB 96c8e59b5950
rl_sample_loo/adapter_step400/adapter_model.safetensorsWeights87.4 MB 1e8d4ac635b9
rl_sample_loo/adapter_step450/adapter_model.safetensorsWeights87.4 MB 5ba3108d26e3
rl_sample_loo/adapter_step50/adapter_model.safetensorsWeights87.4 MB 28dac1c26adb
rl_sample_loo/adapter_step500/adapter_model.safetensorsWeights87.4 MB 1bea0f2fc863
rl_sample_loo/adapter_step550/adapter_model.safetensorsWeights87.4 MB 7bdcabc00a0e
rl_sample_loo/adapter_step600/adapter_model.safetensorsWeights87.4 MB 3c8350294eaf
rl_sample_loo/adapter_step650/adapter_model.safetensorsWeights87.4 MB 69023ebb0ee5
rl_sample_loo/adapter_step700/adapter_model.safetensorsWeights87.4 MB f066d7ab6e99
rl_sample_loo/adapter_step750/adapter_model.safetensorsWeights87.4 MB 609e7008d8e4
rl_sample_loo/adapter_step800/adapter_model.safetensorsWeights87.4 MB 76447092bcd1
rl_sample_loo/adapter_step850/adapter_model.safetensorsWeights87.4 MB d00d11716cf1
rl_sample_loo/adapter_step900/adapter_model.safetensorsWeights87.4 MB 28c843435e89
rl_sample_loo/adapter_step950/adapter_model.safetensorsWeights87.4 MB 252f136a73f1
rloo_lr2e5/adapter_final/adapter_model.safetensorsWeights87.4 MB cfbd61c87728
rloo_lr2e5/adapter_step100/adapter_model.safetensorsWeights87.4 MB 1bcf0dac35a4
rloo_lr2e5/adapter_step1000/adapter_model.safetensorsWeights87.4 MB 5f6b4a9caf9c
rloo_lr2e5/adapter_step1050/adapter_model.safetensorsWeights87.4 MB 7f9ae458e317
rloo_lr2e5/adapter_step1100/adapter_model.safetensorsWeights87.4 MB 0c5504c076ab
rloo_lr2e5/adapter_step1150/adapter_model.safetensorsWeights87.4 MB 97fe92e4a8a9
rloo_lr2e5/adapter_step1200/adapter_model.safetensorsWeights87.4 MB 60b6c20603cc
rloo_lr2e5/adapter_step1250/adapter_model.safetensorsWeights87.4 MB bccf7a731188
rloo_lr2e5/adapter_step1300/adapter_model.safetensorsWeights87.4 MB 5e00ae00ea9e
rloo_lr2e5/adapter_step1350/adapter_model.safetensorsWeights87.4 MB 9955377e2628
rloo_lr2e5/adapter_step1400/adapter_model.safetensorsWeights87.4 MB 9c3f71c5d61c
rloo_lr2e5/adapter_step1450/adapter_model.safetensorsWeights87.4 MB 34033ab9c1e2
rloo_lr2e5/adapter_step150/adapter_model.safetensorsWeights87.4 MB bee219b0dcbc
rloo_lr2e5/adapter_step1500/adapter_model.safetensorsWeights87.4 MB cfbd61c87728
rloo_lr2e5/adapter_step200/adapter_model.safetensorsWeights87.4 MB 85b0e2a12071
rloo_lr2e5/adapter_step250/adapter_model.safetensorsWeights87.4 MB feb81cb5ee80
rloo_lr2e5/adapter_step300/adapter_model.safetensorsWeights87.4 MB 24ba9a087f3c
rloo_lr2e5/adapter_step350/adapter_model.safetensorsWeights87.4 MB 4753ab7669f0
rloo_lr2e5/adapter_step400/adapter_model.safetensorsWeights87.4 MB 9316e497d051
rloo_lr2e5/adapter_step450/adapter_model.safetensorsWeights87.4 MB 25ab45ff7037
rloo_lr2e5/adapter_step50/adapter_model.safetensorsWeights87.4 MB 4c46454fa5eb
rloo_lr2e5/adapter_step500/adapter_model.safetensorsWeights87.4 MB d6689a021dc6
rloo_lr2e5/adapter_step550/adapter_model.safetensorsWeights87.4 MB 724e82008654
rloo_lr2e5/adapter_step600/adapter_model.safetensorsWeights87.4 MB 69465e5a94dd
rloo_lr2e5/adapter_step650/adapter_model.safetensorsWeights87.4 MB 9d44364cd2fd
rloo_lr2e5/adapter_step700/adapter_model.safetensorsWeights87.4 MB 4a3f7f76fbab
rloo_lr2e5/adapter_step750/adapter_model.safetensorsWeights87.4 MB 04a6228d396b
rloo_lr2e5/adapter_step800/adapter_model.safetensorsWeights87.4 MB c7342cd852a1
rloo_lr2e5/adapter_step850/adapter_model.safetensorsWeights87.4 MB 266223fbe8a5
rloo_lr2e5/adapter_step900/adapter_model.safetensorsWeights87.4 MB d3f50f1539bf
rloo_lr2e5/adapter_step950/adapter_model.safetensorsWeights87.4 MB 01a341a39b1a
rloo_lr2e5_cont/adapter_final/adapter_model.safetensorsWeights87.4 MB 9e4aeabf3624
rloo_lr2e5_cont/adapter_step1550/adapter_model.safetensorsWeights87.4 MB 7d34b76c4802
rloo_lr2e5_cont/adapter_step1600/adapter_model.safetensorsWeights87.4 MB e3f9dcc09959
rloo_lr2e5_cont/adapter_step1650/adapter_model.safetensorsWeights87.4 MB cb9104518587
rloo_lr2e5_cont/adapter_step1700/adapter_model.safetensorsWeights87.4 MB 7ccb65ead066
rloo_lr2e5_cont/adapter_step1750/adapter_model.safetensorsWeights87.4 MB bd3ef3580598
rloo_lr2e5_cont/adapter_step1800/adapter_model.safetensorsWeights87.4 MB 6c7615cdf5f9
rloo_lr2e5_cont/adapter_step1850/adapter_model.safetensorsWeights87.4 MB 658460be636d
rloo_lr2e5_cont/adapter_step1900/adapter_model.safetensorsWeights87.4 MB 11bfe1a37dfa
rloo_lr2e5_cont/adapter_step1950/adapter_model.safetensorsWeights87.4 MB c79e910ac7cc
rloo_lr2e5_cont/adapter_step2000/adapter_model.safetensorsWeights87.4 MB ebd106d448f6
rloo_lr2e5_cont/adapter_step2050/adapter_model.safetensorsWeights87.4 MB d3d5b8d640cf
rloo_lr2e5_cont/adapter_step2100/adapter_model.safetensorsWeights87.4 MB f9e6e26b5b8a
rloo_lr2e5_cont/adapter_step2150/adapter_model.safetensorsWeights87.4 MB 24cb3032f297
rloo_lr2e5_cont/adapter_step2200/adapter_model.safetensorsWeights87.4 MB c328a31a7a9a
rloo_lr2e5_cont/adapter_step2250/adapter_model.safetensorsWeights87.4 MB 715b32a3fba1
rloo_lr2e5_cont/adapter_step2300/adapter_model.safetensorsWeights87.4 MB 2d7e57526127
rloo_lr2e5_cont/adapter_step2350/adapter_model.safetensorsWeights87.4 MB b71be29556cf
rloo_lr2e5_cont/adapter_step2400/adapter_model.safetensorsWeights87.4 MB a3ac5e31e34e
rloo_lr2e5_cont/adapter_step2450/adapter_model.safetensorsWeights87.4 MB 0d434c2b3b62
rloo_lr2e5_cont/adapter_step2500/adapter_model.safetensorsWeights87.4 MB 42599cace28e
rloo_lr2e5_cont/adapter_step2550/adapter_model.safetensorsWeights87.4 MB 21c41f8aecd9
rloo_lr2e5_cont/adapter_step2600/adapter_model.safetensorsWeights87.4 MB 0aa93ce49313
rloo_lr2e5_cont/adapter_step2650/adapter_model.safetensorsWeights87.4 MB 825cec208b1d
rloo_lr2e5_cont/adapter_step2700/adapter_model.safetensorsWeights87.4 MB d493b9e10f8e
rloo_lr2e5_cont/adapter_step2750/adapter_model.safetensorsWeights87.4 MB 4c118b2ec993
rloo_lr2e5_cont/adapter_step2800/adapter_model.safetensorsWeights87.4 MB b66187ef55eb
rloo_lr2e5_cont/adapter_step2850/adapter_model.safetensorsWeights87.4 MB 8213cd6fa33d
rloo_lr2e5_cont/adapter_step2900/adapter_model.safetensorsWeights87.4 MB 1efa54ab9948
rloo_lr2e5_cont/adapter_step2950/adapter_model.safetensorsWeights87.4 MB a4c776b8582d
rloo_lr2e5_cont/adapter_step3000/adapter_model.safetensorsWeights87.4 MB 9e4aeabf3624
sft_dense/adapter_final/adapter_model.safetensorsWeights87.4 MB 8f14006327b9
sft_dense/adapter_step100/adapter_model.safetensorsWeights87.4 MB 54ba0aafd462
sft_dense/adapter_step1000/adapter_model.safetensorsWeights87.4 MB 8f14006327b9
sft_dense/adapter_step150/adapter_model.safetensorsWeights87.4 MB fba05d50eaf4
sft_dense/adapter_step200/adapter_model.safetensorsWeights87.4 MB 2559ae1d82b4
sft_dense/adapter_step250/adapter_model.safetensorsWeights87.4 MB fe92c639597f
sft_dense/adapter_step300/adapter_model.safetensorsWeights87.4 MB 8bbbc7322b26
sft_dense/adapter_step350/adapter_model.safetensorsWeights87.4 MB 09678ec920d7
sft_dense/adapter_step400/adapter_model.safetensorsWeights87.4 MB e3d5661292bd
sft_dense/adapter_step450/adapter_model.safetensorsWeights87.4 MB 7d45a52efd94
sft_dense/adapter_step50/adapter_model.safetensorsWeights87.4 MB 883933f5151d
sft_dense/adapter_step500/adapter_model.safetensorsWeights87.4 MB 45d829176664
sft_dense/adapter_step550/adapter_model.safetensorsWeights87.4 MB 70a08aa5270f
sft_dense/adapter_step600/adapter_model.safetensorsWeights87.4 MB fd3b67e2bf40
sft_dense/adapter_step650/adapter_model.safetensorsWeights87.4 MB 05c8df9a13f1
sft_dense/adapter_step700/adapter_model.safetensorsWeights87.4 MB ad37308dfeec
sft_dense/adapter_step750/adapter_model.safetensorsWeights87.4 MB bc691ca7cc8e
sft_dense/adapter_step800/adapter_model.safetensorsWeights87.4 MB 5500efd7bf61
sft_dense/adapter_step850/adapter_model.safetensorsWeights87.4 MB 7387ba10094c
sft_dense/adapter_step900/adapter_model.safetensorsWeights87.4 MB 73469b42e29d
sft_dense/adapter_step950/adapter_model.safetensorsWeights87.4 MB 29da01ee48bc
sft_dense_s7/adapter_final/adapter_model.safetensorsWeights87.4 MB e27586bd5b0b
sft_dense_s7/adapter_step100/adapter_model.safetensorsWeights87.4 MB 46d6161896a7
sft_dense_s7/adapter_step1000/adapter_model.safetensorsWeights87.4 MB e27586bd5b0b
sft_dense_s7/adapter_step150/adapter_model.safetensorsWeights87.4 MB cba3074650e5
sft_dense_s7/adapter_step200/adapter_model.safetensorsWeights87.4 MB faf67872282c
sft_dense_s7/adapter_step250/adapter_model.safetensorsWeights87.4 MB 39b02d3ca8b7
sft_dense_s7/adapter_step300/adapter_model.safetensorsWeights87.4 MB 78e6b210dbd1
sft_dense_s7/adapter_step350/adapter_model.safetensorsWeights87.4 MB b4cd4df7d1eb
sft_dense_s7/adapter_step400/adapter_model.safetensorsWeights87.4 MB ad10d19e4f27
sft_dense_s7/adapter_step450/adapter_model.safetensorsWeights87.4 MB 7e46a726f0a5
sft_dense_s7/adapter_step50/adapter_model.safetensorsWeights87.4 MB 3bc008d0126c
sft_dense_s7/adapter_step500/adapter_model.safetensorsWeights87.4 MB bc1950f361e2
sft_dense_s7/adapter_step550/adapter_model.safetensorsWeights87.4 MB f5f1f1917b79
sft_dense_s7/adapter_step600/adapter_model.safetensorsWeights87.4 MB 6c22439c9fc0
sft_dense_s7/adapter_step650/adapter_model.safetensorsWeights87.4 MB a2bff86ad5d5
sft_dense_s7/adapter_step700/adapter_model.safetensorsWeights87.4 MB 706d49331692
sft_dense_s7/adapter_step750/adapter_model.safetensorsWeights87.4 MB 0a2437f6295f
sft_dense_s7/adapter_step800/adapter_model.safetensorsWeights87.4 MB 249fc9ff9ad4
sft_dense_s7/adapter_step850/adapter_model.safetensorsWeights87.4 MB 06a11796c791
sft_dense_s7/adapter_step900/adapter_model.safetensorsWeights87.4 MB acefea4ac67b
sft_dense_s7/adapter_step950/adapter_model.safetensorsWeights87.4 MB 77f26531187f
sft_lr2e5/adapter_final/adapter_model.safetensorsWeights87.4 MB aa6683d2df67
sft_lr2e5/adapter_step100/adapter_model.safetensorsWeights87.4 MB 3d012e0b6247
sft_lr2e5/adapter_step1000/adapter_model.safetensorsWeights87.4 MB 8f67781b6603
sft_lr2e5/adapter_step1050/adapter_model.safetensorsWeights87.4 MB 7c934e504237
sft_lr2e5/adapter_step1100/adapter_model.safetensorsWeights87.4 MB fc465750a040
sft_lr2e5/adapter_step1150/adapter_model.safetensorsWeights87.4 MB c7afdd48052e
sft_lr2e5/adapter_step1200/adapter_model.safetensorsWeights87.4 MB e6958180c45e
sft_lr2e5/adapter_step1250/adapter_model.safetensorsWeights87.4 MB cb3a958f7576
sft_lr2e5/adapter_step1300/adapter_model.safetensorsWeights87.4 MB e472e849d2ee
sft_lr2e5/adapter_step1350/adapter_model.safetensorsWeights87.4 MB 300acfb4cb7c
sft_lr2e5/adapter_step1400/adapter_model.safetensorsWeights87.4 MB 8764dd2761b1
sft_lr2e5/adapter_step1450/adapter_model.safetensorsWeights87.4 MB 8a03f4d4ba80
sft_lr2e5/adapter_step150/adapter_model.safetensorsWeights87.4 MB 4befb95fbfe1
sft_lr2e5/adapter_step1500/adapter_model.safetensorsWeights87.4 MB aa6683d2df67
sft_lr2e5/adapter_step200/adapter_model.safetensorsWeights87.4 MB aeedaebb1337
sft_lr2e5/adapter_step250/adapter_model.safetensorsWeights87.4 MB 02024b2b78d0
sft_lr2e5/adapter_step300/adapter_model.safetensorsWeights87.4 MB e6b730d2e298
sft_lr2e5/adapter_step350/adapter_model.safetensorsWeights87.4 MB 6fdd114352b8
sft_lr2e5/adapter_step400/adapter_model.safetensorsWeights87.4 MB 7241d8ac208f
sft_lr2e5/adapter_step450/adapter_model.safetensorsWeights87.4 MB 78733865e46b
sft_lr2e5/adapter_step50/adapter_model.safetensorsWeights87.4 MB e996e90bd2df
sft_lr2e5/adapter_step500/adapter_model.safetensorsWeights87.4 MB 8e389d5723e8
sft_lr2e5/adapter_step550/adapter_model.safetensorsWeights87.4 MB 3b01e6e69201
sft_lr2e5/adapter_step600/adapter_model.safetensorsWeights87.4 MB c8c460a28353
sft_lr2e5/adapter_step650/adapter_model.safetensorsWeights87.4 MB a3f45dbfa0b9
sft_lr2e5/adapter_step700/adapter_model.safetensorsWeights87.4 MB 6a468c9482bd
sft_lr2e5/adapter_step750/adapter_model.safetensorsWeights87.4 MB 0de71fd8dd12
sft_lr2e5/adapter_step800/adapter_model.safetensorsWeights87.4 MB 37665313b354
sft_lr2e5/adapter_step850/adapter_model.safetensorsWeights87.4 MB 7f7a011a51e0
sft_lr2e5/adapter_step900/adapter_model.safetensorsWeights87.4 MB 210b0a0ffb7f
sft_lr2e5/adapter_step950/adapter_model.safetensorsWeights87.4 MB 62cbaad59f34
sft_lr2e5_s7/adapter_final/adapter_model.safetensorsWeights87.4 MB dd0101aea338
sft_lr2e5_s7/adapter_step100/adapter_model.safetensorsWeights87.4 MB 86e1fd781c39
sft_lr2e5_s7/adapter_step1000/adapter_model.safetensorsWeights87.4 MB 3745f66d05b3
sft_lr2e5_s7/adapter_step1050/adapter_model.safetensorsWeights87.4 MB 2b4f6b962c92
sft_lr2e5_s7/adapter_step1100/adapter_model.safetensorsWeights87.4 MB 19885cd1b04f
sft_lr2e5_s7/adapter_step1150/adapter_model.safetensorsWeights87.4 MB adfa8ae9fe7d
sft_lr2e5_s7/adapter_step1200/adapter_model.safetensorsWeights87.4 MB 472d2187ee8d
sft_lr2e5_s7/adapter_step1250/adapter_model.safetensorsWeights87.4 MB 6f26084908cc
sft_lr2e5_s7/adapter_step1300/adapter_model.safetensorsWeights87.4 MB 268f69a4808d
sft_lr2e5_s7/adapter_step1350/adapter_model.safetensorsWeights87.4 MB 08e6a1c97bd4
sft_lr2e5_s7/adapter_step1400/adapter_model.safetensorsWeights87.4 MB 2d777f31d87d
sft_lr2e5_s7/adapter_step1450/adapter_model.safetensorsWeights87.4 MB 28f5de3bca9b
sft_lr2e5_s7/adapter_step150/adapter_model.safetensorsWeights87.4 MB 50cad05e7345
sft_lr2e5_s7/adapter_step1500/adapter_model.safetensorsWeights87.4 MB dd0101aea338
sft_lr2e5_s7/adapter_step200/adapter_model.safetensorsWeights87.4 MB e5a51ca10b41
sft_lr2e5_s7/adapter_step250/adapter_model.safetensorsWeights87.4 MB 699daca44e98
sft_lr2e5_s7/adapter_step300/adapter_model.safetensorsWeights87.4 MB bc0050b2c7e4
sft_lr2e5_s7/adapter_step350/adapter_model.safetensorsWeights87.4 MB 2aa2c9a2331d
sft_lr2e5_s7/adapter_step400/adapter_model.safetensorsWeights87.4 MB 903fa6b7e3e5
sft_lr2e5_s7/adapter_step450/adapter_model.safetensorsWeights87.4 MB 615f20e9c476
sft_lr2e5_s7/adapter_step50/adapter_model.safetensorsWeights87.4 MB fb99ca866d23
sft_lr2e5_s7/adapter_step500/adapter_model.safetensorsWeights87.4 MB bea07407734e
sft_lr2e5_s7/adapter_step550/adapter_model.safetensorsWeights87.4 MB 98e1fc3a9091
sft_lr2e5_s7/adapter_step600/adapter_model.safetensorsWeights87.4 MB f7f0ea755d27
sft_lr2e5_s7/adapter_step650/adapter_model.safetensorsWeights87.4 MB 29ed67efacf2
sft_lr2e5_s7/adapter_step700/adapter_model.safetensorsWeights87.4 MB 7119b11b58fb
sft_lr2e5_s7/adapter_step750/adapter_model.safetensorsWeights87.4 MB b0de1b43e573
sft_lr2e5_s7/adapter_step800/adapter_model.safetensorsWeights87.4 MB 378b5aefd14c
sft_lr2e5_s7/adapter_step850/adapter_model.safetensorsWeights87.4 MB 62982cb4394c
sft_lr2e5_s7/adapter_step900/adapter_model.safetensorsWeights87.4 MB f418e02584f8
sft_lr2e5_s7/adapter_step950/adapter_model.safetensorsWeights87.4 MB 0cb3e9482877
dpo/adapter_final/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step100/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step1000/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step1050/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step1100/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step1150/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step1200/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step1250/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step1300/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step1350/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step1400/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step1450/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step150/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step1500/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step200/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step250/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step300/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step350/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step400/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step450/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step50/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step500/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step550/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step600/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step650/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step700/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step750/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step800/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step850/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step900/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_step950/adapter_config.jsonConfiguration1.2 KB —
results/dpo/args.jsonConfiguration567 B —
results/dpo/eval_step1000.jsonConfiguration55.1 KB —
results/dpo/eval_step1250.jsonConfiguration55.2 KB —
results/dpo/eval_step1500.jsonConfiguration55.1 KB —
results/dpo/eval_step250.jsonConfiguration55.9 KB —
results/dpo/eval_step500.jsonConfiguration55.7 KB —
results/dpo/eval_step750.jsonConfiguration55.1 KB —
results/rl_exact_ent/args.jsonConfiguration582 B —
results/rl_exact_ent/eval_step250.jsonConfiguration56.0 KB —
results/rl_exact_ent/eval_step500.jsonConfiguration54.6 KB —
results/rl_exact_ent/eval_step750.jsonConfiguration54.7 KB —
results/rl_exact_lr2e5/args.jsonConfiguration583 B —
results/rl_exact_lr2e5/eval_step1000.jsonConfiguration56.0 KB —
results/rl_exact_lr2e5/eval_step1250.jsonConfiguration56.1 KB —
results/rl_exact_lr2e5/eval_step1500.jsonConfiguration55.8 KB —
results/rl_exact_lr2e5/eval_step250.jsonConfiguration55.9 KB —
results/rl_exact_lr2e5/eval_step500.jsonConfiguration55.9 KB —
results/rl_exact_lr2e5/eval_step750.jsonConfiguration56.1 KB —
results/rl_exact_lr2e5_cont/args.jsonConfiguration662 B —
results/rl_exact_lr2e5_cont/eval_step1750.jsonConfiguration55.8 KB —
results/rl_exact_lr2e5_cont/eval_step2000.jsonConfiguration55.8 KB —
results/rl_exact_lr2e5_cont/eval_step2250.jsonConfiguration55.8 KB —
results/rl_exact_lr2e5_cont/eval_step2500.jsonConfiguration55.8 KB —
results/rl_exact_lr2e5_cont/eval_step2750.jsonConfiguration55.6 KB —
results/rl_exact_lr2e5_cont/eval_step3000.jsonConfiguration56.0 KB —
results/rl_exact_lr2e5_s7/args.jsonConfiguration618 B —
results/rl_exact_lr2e5_s7/eval_step1000.jsonConfiguration56.1 KB —
results/rl_exact_lr2e5_s7/eval_step1500.jsonConfiguration56.0 KB —
results/rl_exact_lr2e5_s7/eval_step500.jsonConfiguration55.9 KB —
results/rl_norm_lr2e5/args.jsonConfiguration581 B —
results/rl_norm_lr2e5/eval_step1000.jsonConfiguration54.8 KB —
results/rl_norm_lr2e5/eval_step1250.jsonConfiguration54.7 KB —
results/rl_norm_lr2e5/eval_step1500.jsonConfiguration55.1 KB —
results/rl_norm_lr2e5/eval_step250.jsonConfiguration55.8 KB —
results/rl_norm_lr2e5/eval_step500.jsonConfiguration55.6 KB —
results/rl_norm_lr2e5/eval_step750.jsonConfiguration55.7 KB —
results/rl_sample_loo/args.jsonConfiguration582 B —
results/rl_sample_loo/eval_step250.jsonConfiguration54.9 KB —
results/rl_sample_loo/eval_step500.jsonConfiguration54.7 KB —
results/rl_sample_loo/eval_step750.jsonConfiguration55.1 KB —
results/rloo_lr2e5/args.jsonConfiguration580 B —
results/rloo_lr2e5/eval_step1000.jsonConfiguration55.8 KB —
results/rloo_lr2e5/eval_step1250.jsonConfiguration56.1 KB —
results/rloo_lr2e5/eval_step1500.jsonConfiguration55.5 KB —
results/rloo_lr2e5/eval_step250.jsonConfiguration55.9 KB —
results/rloo_lr2e5/eval_step500.jsonConfiguration56.1 KB —
results/rloo_lr2e5/eval_step750.jsonConfiguration56.1 KB —
results/rloo_lr2e5_cont/args.jsonConfiguration655 B —
results/rloo_lr2e5_cont/eval_step1750.jsonConfiguration55.7 KB —
results/rloo_lr2e5_cont/eval_step2000.jsonConfiguration55.9 KB —
results/rloo_lr2e5_cont/eval_step2250.jsonConfiguration56.1 KB —
results/rloo_lr2e5_cont/eval_step2500.jsonConfiguration55.8 KB —
results/rloo_lr2e5_cont/eval_step2750.jsonConfiguration56.2 KB —
results/rloo_lr2e5_cont/eval_step3000.jsonConfiguration55.9 KB —
results/sft_dense/args.jsonConfiguration574 B —
results/sft_dense/eval_step0.jsonConfiguration55.9 KB —
results/sft_dense/eval_step1000.jsonConfiguration55.6 KB —
results/sft_dense/eval_step250.jsonConfiguration56.1 KB —
results/sft_dense/eval_step500.jsonConfiguration56.1 KB —
results/sft_dense/eval_step750.jsonConfiguration55.6 KB —
results/sft_dense/reeval_step300.jsonConfiguration44.5 KB —
results/sft_dense/reeval_step350.jsonConfiguration44.7 KB —
results/sft_dense/reeval_step400.jsonConfiguration44.5 KB —
results/sft_dense/reeval_step450.jsonConfiguration44.3 KB —
results/sft_dense/reeval_step550.jsonConfiguration44.2 KB —
results/sft_dense/reeval_step600.jsonConfiguration44.0 KB —
results/sft_dense/reeval_step650.jsonConfiguration44.4 KB —
results/sft_dense/reeval_step700.jsonConfiguration44.0 KB —
results/sft_dense_s7/args.jsonConfiguration608 B —
results/sft_dense_s7/eval_step1000.jsonConfiguration55.4 KB —
results/sft_dense_s7/eval_step250.jsonConfiguration56.1 KB —
results/sft_dense_s7/eval_step500.jsonConfiguration56.0 KB —
results/sft_dense_s7/eval_step750.jsonConfiguration55.6 KB —
results/sft_lr2e5/args.jsonConfiguration572 B —
results/sft_lr2e5/eval_step1000.jsonConfiguration56.2 KB —
results/sft_lr2e5/eval_step1250.jsonConfiguration55.8 KB —
results/sft_lr2e5/eval_step1500.jsonConfiguration55.7 KB —
results/sft_lr2e5/eval_step250.jsonConfiguration56.0 KB —
results/sft_lr2e5/eval_step500.jsonConfiguration56.0 KB —
results/sft_lr2e5/eval_step750.jsonConfiguration55.9 KB —
results/sft_lr2e5_s7/args.jsonConfiguration607 B —
results/sft_lr2e5_s7/eval_step1000.jsonConfiguration56.0 KB —
results/sft_lr2e5_s7/eval_step1250.jsonConfiguration56.0 KB —
results/sft_lr2e5_s7/eval_step1500.jsonConfiguration56.2 KB —
results/sft_lr2e5_s7/eval_step250.jsonConfiguration56.0 KB —
results/sft_lr2e5_s7/eval_step500.jsonConfiguration55.8 KB —
results/sft_lr2e5_s7/eval_step750.jsonConfiguration55.9 KB —
rl_exact_ent/adapter_step100/adapter_config.jsonConfiguration1.2 KB —
rl_exact_ent/adapter_step150/adapter_config.jsonConfiguration1.2 KB —
rl_exact_ent/adapter_step200/adapter_config.jsonConfiguration1.2 KB —
rl_exact_ent/adapter_step250/adapter_config.jsonConfiguration1.2 KB —
rl_exact_ent/adapter_step300/adapter_config.jsonConfiguration1.2 KB —
rl_exact_ent/adapter_step350/adapter_config.jsonConfiguration1.2 KB —
rl_exact_ent/adapter_step400/adapter_config.jsonConfiguration1.2 KB —
rl_exact_ent/adapter_step450/adapter_config.jsonConfiguration1.2 KB —
rl_exact_ent/adapter_step50/adapter_config.jsonConfiguration1.2 KB —
rl_exact_ent/adapter_step500/adapter_config.jsonConfiguration1.2 KB —
rl_exact_ent/adapter_step550/adapter_config.jsonConfiguration1.2 KB —
rl_exact_ent/adapter_step600/adapter_config.jsonConfiguration1.2 KB —
rl_exact_ent/adapter_step650/adapter_config.jsonConfiguration1.2 KB —
rl_exact_ent/adapter_step700/adapter_config.jsonConfiguration1.2 KB —
rl_exact_ent/adapter_step750/adapter_config.jsonConfiguration1.2 KB —
rl_exact_ent/adapter_step800/adapter_config.jsonConfiguration1.2 KB —
rl_exact_ent/adapter_step850/adapter_config.jsonConfiguration1.2 KB —
rl_exact_ent/adapter_step900/adapter_config.jsonConfiguration1.2 KB —
rl_exact_ent/adapter_step950/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_final/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step100/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step1000/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step1050/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step1100/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step1150/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step1200/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step1250/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step1300/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step1350/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step1400/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step1450/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step150/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step1500/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step200/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step250/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step300/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step350/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step400/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step450/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step50/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step500/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step550/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step600/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step650/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step700/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step750/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step800/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step850/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step900/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5/adapter_step950/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_final/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step1550/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step1600/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step1650/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step1700/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step1750/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step1800/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step1850/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step1900/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step1950/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step2000/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step2050/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step2100/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step2150/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step2200/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step2250/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step2300/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step2350/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step2400/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step2450/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step2500/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step2550/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step2600/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step2650/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step2700/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step2750/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step2800/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step2850/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step2900/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step2950/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_cont/adapter_step3000/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step100/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step1000/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step1050/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step1100/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step1150/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step1200/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step1250/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step1300/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step1350/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step1400/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step1450/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step150/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step1500/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step1550/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step1600/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step1650/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step1700/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step1750/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step1800/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step1850/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step1900/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step1950/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step200/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step250/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step300/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step350/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step400/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step450/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step50/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step500/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step550/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step600/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step650/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step700/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step750/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step800/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step850/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step900/adapter_config.jsonConfiguration1.2 KB —
rl_exact_lr2e5_s7/adapter_step950/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_final/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step100/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step1000/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step1050/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step1100/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step1150/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step1200/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step1250/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step1300/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step1350/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step1400/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step1450/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step150/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step1500/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step200/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step250/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step300/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step350/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step400/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step450/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step50/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step500/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step550/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step600/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step650/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step700/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step750/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step800/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step850/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step900/adapter_config.jsonConfiguration1.2 KB —
rl_norm_lr2e5/adapter_step950/adapter_config.jsonConfiguration1.2 KB —
rl_sample_loo/adapter_step100/adapter_config.jsonConfiguration1.2 KB —
rl_sample_loo/adapter_step150/adapter_config.jsonConfiguration1.2 KB —
rl_sample_loo/adapter_step200/adapter_config.jsonConfiguration1.2 KB —
rl_sample_loo/adapter_step250/adapter_config.jsonConfiguration1.2 KB —
rl_sample_loo/adapter_step300/adapter_config.jsonConfiguration1.2 KB —
rl_sample_loo/adapter_step350/adapter_config.jsonConfiguration1.2 KB —
rl_sample_loo/adapter_step400/adapter_config.jsonConfiguration1.2 KB —
rl_sample_loo/adapter_step450/adapter_config.jsonConfiguration1.2 KB —
rl_sample_loo/adapter_step50/adapter_config.jsonConfiguration1.2 KB —
rl_sample_loo/adapter_step500/adapter_config.jsonConfiguration1.2 KB —
rl_sample_loo/adapter_step550/adapter_config.jsonConfiguration1.2 KB —
rl_sample_loo/adapter_step600/adapter_config.jsonConfiguration1.2 KB —
rl_sample_loo/adapter_step650/adapter_config.jsonConfiguration1.2 KB —
rl_sample_loo/adapter_step700/adapter_config.jsonConfiguration1.2 KB —
rl_sample_loo/adapter_step750/adapter_config.jsonConfiguration1.2 KB —
rl_sample_loo/adapter_step800/adapter_config.jsonConfiguration1.2 KB —
rl_sample_loo/adapter_step850/adapter_config.jsonConfiguration1.2 KB —
rl_sample_loo/adapter_step900/adapter_config.jsonConfiguration1.2 KB —
rl_sample_loo/adapter_step950/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_final/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step100/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step1000/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step1050/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step1100/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step1150/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step1200/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step1250/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step1300/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step1350/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step1400/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step1450/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step150/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step1500/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step200/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step250/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step300/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step350/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step400/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step450/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step50/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step500/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step550/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step600/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step650/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step700/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step750/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step800/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step850/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step900/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5/adapter_step950/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_final/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step1550/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step1600/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step1650/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step1700/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step1750/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step1800/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step1850/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step1900/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step1950/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step2000/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step2050/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step2100/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step2150/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step2200/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step2250/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step2300/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step2350/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step2400/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step2450/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step2500/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step2550/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step2600/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step2650/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step2700/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step2750/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step2800/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step2850/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step2900/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step2950/adapter_config.jsonConfiguration1.2 KB —
rloo_lr2e5_cont/adapter_step3000/adapter_config.jsonConfiguration1.2 KB —
sft_dense/adapter_final/adapter_config.jsonConfiguration1.2 KB —
sft_dense/adapter_step100/adapter_config.jsonConfiguration1.2 KB —
sft_dense/adapter_step1000/adapter_config.jsonConfiguration1.2 KB —
sft_dense/adapter_step150/adapter_config.jsonConfiguration1.2 KB —
sft_dense/adapter_step200/adapter_config.jsonConfiguration1.2 KB —
sft_dense/adapter_step250/adapter_config.jsonConfiguration1.2 KB —
sft_dense/adapter_step300/adapter_config.jsonConfiguration1.2 KB —
sft_dense/adapter_step350/adapter_config.jsonConfiguration1.2 KB —
sft_dense/adapter_step400/adapter_config.jsonConfiguration1.2 KB —
sft_dense/adapter_step450/adapter_config.jsonConfiguration1.2 KB —
sft_dense/adapter_step50/adapter_config.jsonConfiguration1.2 KB —
sft_dense/adapter_step500/adapter_config.jsonConfiguration1.2 KB —
sft_dense/adapter_step550/adapter_config.jsonConfiguration1.2 KB —
sft_dense/adapter_step600/adapter_config.jsonConfiguration1.2 KB —
sft_dense/adapter_step650/adapter_config.jsonConfiguration1.2 KB —
sft_dense/adapter_step700/adapter_config.jsonConfiguration1.2 KB —
sft_dense/adapter_step750/adapter_config.jsonConfiguration1.2 KB —
sft_dense/adapter_step800/adapter_config.jsonConfiguration1.2 KB —
sft_dense/adapter_step850/adapter_config.jsonConfiguration1.2 KB —
sft_dense/adapter_step900/adapter_config.jsonConfiguration1.2 KB —
sft_dense/adapter_step950/adapter_config.jsonConfiguration1.2 KB —
sft_dense_s7/adapter_final/adapter_config.jsonConfiguration1.2 KB —
sft_dense_s7/adapter_step100/adapter_config.jsonConfiguration1.2 KB —
sft_dense_s7/adapter_step1000/adapter_config.jsonConfiguration1.2 KB —
sft_dense_s7/adapter_step150/adapter_config.jsonConfiguration1.2 KB —
sft_dense_s7/adapter_step200/adapter_config.jsonConfiguration1.2 KB —
sft_dense_s7/adapter_step250/adapter_config.jsonConfiguration1.2 KB —
sft_dense_s7/adapter_step300/adapter_config.jsonConfiguration1.2 KB —
sft_dense_s7/adapter_step350/adapter_config.jsonConfiguration1.2 KB —
sft_dense_s7/adapter_step400/adapter_config.jsonConfiguration1.2 KB —
sft_dense_s7/adapter_step450/adapter_config.jsonConfiguration1.2 KB —
sft_dense_s7/adapter_step50/adapter_config.jsonConfiguration1.2 KB —
sft_dense_s7/adapter_step500/adapter_config.jsonConfiguration1.2 KB —
sft_dense_s7/adapter_step550/adapter_config.jsonConfiguration1.2 KB —
sft_dense_s7/adapter_step600/adapter_config.jsonConfiguration1.2 KB —
sft_dense_s7/adapter_step650/adapter_config.jsonConfiguration1.2 KB —
sft_dense_s7/adapter_step700/adapter_config.jsonConfiguration1.2 KB —
sft_dense_s7/adapter_step750/adapter_config.jsonConfiguration1.2 KB —
sft_dense_s7/adapter_step800/adapter_config.jsonConfiguration1.2 KB —
sft_dense_s7/adapter_step850/adapter_config.jsonConfiguration1.2 KB —
sft_dense_s7/adapter_step900/adapter_config.jsonConfiguration1.2 KB —
sft_dense_s7/adapter_step950/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_final/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step100/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step1000/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step1050/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step1100/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step1150/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step1200/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step1250/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step1300/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step1350/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step1400/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step1450/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step150/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step1500/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step200/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step250/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step300/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step350/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step400/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step450/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step50/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step500/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step550/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step600/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step650/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step700/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step750/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step800/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step850/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step900/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5/adapter_step950/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_final/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step100/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step1000/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step1050/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step1100/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step1150/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step1200/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step1250/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step1300/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step1350/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step1400/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step1450/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step150/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step1500/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step200/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step250/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step300/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step350/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step400/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step450/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step50/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step500/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step550/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step600/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step650/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step700/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step750/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step800/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step850/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step900/adapter_config.jsonConfiguration1.2 KB —
sft_lr2e5_s7/adapter_step950/adapter_config.jsonConfiguration1.2 KB —
dpo/adapter_final/README.mdDocumentation5.2 KB —
dpo/adapter_step100/README.mdDocumentation5.2 KB —
dpo/adapter_step1000/README.mdDocumentation5.2 KB —
dpo/adapter_step1050/README.mdDocumentation5.2 KB —
dpo/adapter_step1100/README.mdDocumentation5.2 KB —
dpo/adapter_step1150/README.mdDocumentation5.2 KB —
dpo/adapter_step1200/README.mdDocumentation5.2 KB —
dpo/adapter_step1250/README.mdDocumentation5.2 KB —
dpo/adapter_step1300/README.mdDocumentation5.2 KB —
dpo/adapter_step1350/README.mdDocumentation5.2 KB —
dpo/adapter_step1400/README.mdDocumentation5.2 KB —
dpo/adapter_step1450/README.mdDocumentation5.2 KB —
dpo/adapter_step150/README.mdDocumentation5.2 KB —
dpo/adapter_step1500/README.mdDocumentation5.2 KB —
dpo/adapter_step200/README.mdDocumentation5.2 KB —
dpo/adapter_step250/README.mdDocumentation5.2 KB —
dpo/adapter_step300/README.mdDocumentation5.2 KB —
dpo/adapter_step350/README.mdDocumentation5.2 KB —
dpo/adapter_step400/README.mdDocumentation5.2 KB —
dpo/adapter_step450/README.mdDocumentation5.2 KB —
dpo/adapter_step50/README.mdDocumentation5.2 KB —
dpo/adapter_step500/README.mdDocumentation5.2 KB —
dpo/adapter_step550/README.mdDocumentation5.2 KB —
dpo/adapter_step600/README.mdDocumentation5.2 KB —
dpo/adapter_step650/README.mdDocumentation5.2 KB —
dpo/adapter_step700/README.mdDocumentation5.2 KB —
dpo/adapter_step750/README.mdDocumentation5.2 KB —
dpo/adapter_step800/README.mdDocumentation5.2 KB —
dpo/adapter_step850/README.mdDocumentation5.2 KB —
dpo/adapter_step900/README.mdDocumentation5.2 KB —
dpo/adapter_step950/README.mdDocumentation5.2 KB —
rl_exact_ent/adapter_step100/README.mdDocumentation5.2 KB —
rl_exact_ent/adapter_step150/README.mdDocumentation5.2 KB —
rl_exact_ent/adapter_step200/README.mdDocumentation5.2 KB —
rl_exact_ent/adapter_step250/README.mdDocumentation5.2 KB —
rl_exact_ent/adapter_step300/README.mdDocumentation5.2 KB —
rl_exact_ent/adapter_step350/README.mdDocumentation5.2 KB —
rl_exact_ent/adapter_step400/README.mdDocumentation5.2 KB —
rl_exact_ent/adapter_step450/README.mdDocumentation5.2 KB —
rl_exact_ent/adapter_step50/README.mdDocumentation5.2 KB —
rl_exact_ent/adapter_step500/README.mdDocumentation5.2 KB —
rl_exact_ent/adapter_step550/README.mdDocumentation5.2 KB —
rl_exact_ent/adapter_step600/README.mdDocumentation5.2 KB —
rl_exact_ent/adapter_step650/README.mdDocumentation5.2 KB —
rl_exact_ent/adapter_step700/README.mdDocumentation5.2 KB —
rl_exact_ent/adapter_step750/README.mdDocumentation5.2 KB —
rl_exact_ent/adapter_step800/README.mdDocumentation5.2 KB —
rl_exact_ent/adapter_step850/README.mdDocumentation5.2 KB —
rl_exact_ent/adapter_step900/README.mdDocumentation5.2 KB —
rl_exact_ent/adapter_step950/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_final/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step100/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step1000/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step1050/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step1100/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step1150/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step1200/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step1250/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step1300/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step1350/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step1400/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step1450/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step150/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step1500/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step200/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step250/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step300/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step350/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step400/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step450/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step50/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step500/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step550/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step600/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step650/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step700/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step750/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step800/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step850/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step900/README.mdDocumentation5.2 KB —
rl_exact_lr2e5/adapter_step950/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_final/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step1550/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step1600/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step1650/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step1700/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step1750/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step1800/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step1850/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step1900/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step1950/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step2000/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step2050/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step2100/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step2150/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step2200/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step2250/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step2300/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step2350/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step2400/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step2450/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step2500/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step2550/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step2600/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step2650/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step2700/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step2750/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step2800/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step2850/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step2900/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step2950/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_cont/adapter_step3000/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step100/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step1000/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step1050/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step1100/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step1150/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step1200/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step1250/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step1300/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step1350/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step1400/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step1450/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step150/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step1500/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step1550/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step1600/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step1650/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step1700/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step1750/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step1800/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step1850/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step1900/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step1950/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step200/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step250/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step300/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step350/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step400/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step450/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step50/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step500/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step550/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step600/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step650/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step700/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step750/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step800/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step850/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step900/README.mdDocumentation5.2 KB —
rl_exact_lr2e5_s7/adapter_step950/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_final/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step100/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step1000/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step1050/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step1100/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step1150/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step1200/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step1250/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step1300/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step1350/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step1400/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step1450/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step150/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step1500/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step200/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step250/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step300/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step350/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step400/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step450/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step50/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step500/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step550/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step600/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step650/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step700/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step750/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step800/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step850/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step900/README.mdDocumentation5.2 KB —
rl_norm_lr2e5/adapter_step950/README.mdDocumentation5.2 KB —
rl_sample_loo/adapter_step100/README.mdDocumentation5.2 KB —
rl_sample_loo/adapter_step150/README.mdDocumentation5.2 KB —
rl_sample_loo/adapter_step200/README.mdDocumentation5.2 KB —
rl_sample_loo/adapter_step250/README.mdDocumentation5.2 KB —
rl_sample_loo/adapter_step300/README.mdDocumentation5.2 KB —
rl_sample_loo/adapter_step350/README.mdDocumentation5.2 KB —
rl_sample_loo/adapter_step400/README.mdDocumentation5.2 KB —
rl_sample_loo/adapter_step450/README.mdDocumentation5.2 KB —
rl_sample_loo/adapter_step50/README.mdDocumentation5.2 KB —
rl_sample_loo/adapter_step500/README.mdDocumentation5.2 KB —
rl_sample_loo/adapter_step550/README.mdDocumentation5.2 KB —
rl_sample_loo/adapter_step600/README.mdDocumentation5.2 KB —
rl_sample_loo/adapter_step650/README.mdDocumentation5.2 KB —
rl_sample_loo/adapter_step700/README.mdDocumentation5.2 KB —
rl_sample_loo/adapter_step750/README.mdDocumentation5.2 KB —
rl_sample_loo/adapter_step800/README.mdDocumentation5.2 KB —
rl_sample_loo/adapter_step850/README.mdDocumentation5.2 KB —
rl_sample_loo/adapter_step900/README.mdDocumentation5.2 KB —
rl_sample_loo/adapter_step950/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_final/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step100/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step1000/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step1050/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step1100/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step1150/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step1200/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step1250/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step1300/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step1350/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step1400/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step1450/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step150/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step1500/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step200/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step250/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step300/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step350/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step400/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step450/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step50/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step500/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step550/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step600/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step650/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step700/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step750/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step800/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step850/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step900/README.mdDocumentation5.2 KB —
rloo_lr2e5/adapter_step950/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_final/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step1550/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step1600/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step1650/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step1700/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step1750/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step1800/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step1850/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step1900/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step1950/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step2000/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step2050/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step2100/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step2150/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step2200/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step2250/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step2300/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step2350/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step2400/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step2450/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step2500/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step2550/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step2600/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step2650/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step2700/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step2750/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step2800/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step2850/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step2900/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step2950/README.mdDocumentation5.2 KB —
rloo_lr2e5_cont/adapter_step3000/README.mdDocumentation5.2 KB —
sft_dense/adapter_final/README.mdDocumentation5.2 KB —
sft_dense/adapter_step100/README.mdDocumentation5.2 KB —
sft_dense/adapter_step1000/README.mdDocumentation5.2 KB —
sft_dense/adapter_step150/README.mdDocumentation5.2 KB —
sft_dense/adapter_step200/README.mdDocumentation5.2 KB —
sft_dense/adapter_step250/README.mdDocumentation5.2 KB —
sft_dense/adapter_step300/README.mdDocumentation5.2 KB —
sft_dense/adapter_step350/README.mdDocumentation5.2 KB —
sft_dense/adapter_step400/README.mdDocumentation5.2 KB —
sft_dense/adapter_step450/README.mdDocumentation5.2 KB —
sft_dense/adapter_step50/README.mdDocumentation5.2 KB —
sft_dense/adapter_step500/README.mdDocumentation5.2 KB —
sft_dense/adapter_step550/README.mdDocumentation5.2 KB —
sft_dense/adapter_step600/README.mdDocumentation5.2 KB —
sft_dense/adapter_step650/README.mdDocumentation5.2 KB —
sft_dense/adapter_step700/README.mdDocumentation5.2 KB —
sft_dense/adapter_step750/README.mdDocumentation5.2 KB —
sft_dense/adapter_step800/README.mdDocumentation5.2 KB —
sft_dense/adapter_step850/README.mdDocumentation5.2 KB —
sft_dense/adapter_step900/README.mdDocumentation5.2 KB —
sft_dense/adapter_step950/README.mdDocumentation5.2 KB —
sft_dense_s7/adapter_final/README.mdDocumentation5.2 KB —
sft_dense_s7/adapter_step100/README.mdDocumentation5.2 KB —
sft_dense_s7/adapter_step1000/README.mdDocumentation5.2 KB —
sft_dense_s7/adapter_step150/README.mdDocumentation5.2 KB —
sft_dense_s7/adapter_step200/README.mdDocumentation5.2 KB —
sft_dense_s7/adapter_step250/README.mdDocumentation5.2 KB —
sft_dense_s7/adapter_step300/README.mdDocumentation5.2 KB —
sft_dense_s7/adapter_step350/README.mdDocumentation5.2 KB —
sft_dense_s7/adapter_step400/README.mdDocumentation5.2 KB —
sft_dense_s7/adapter_step450/README.mdDocumentation5.2 KB —
sft_dense_s7/adapter_step50/README.mdDocumentation5.2 KB —
sft_dense_s7/adapter_step500/README.mdDocumentation5.2 KB —
sft_dense_s7/adapter_step550/README.mdDocumentation5.2 KB —
sft_dense_s7/adapter_step600/README.mdDocumentation5.2 KB —
sft_dense_s7/adapter_step650/README.mdDocumentation5.2 KB —
sft_dense_s7/adapter_step700/README.mdDocumentation5.2 KB —
sft_dense_s7/adapter_step750/README.mdDocumentation5.2 KB —
sft_dense_s7/adapter_step800/README.mdDocumentation5.2 KB —
sft_dense_s7/adapter_step850/README.mdDocumentation5.2 KB —
sft_dense_s7/adapter_step900/README.mdDocumentation5.2 KB —
sft_dense_s7/adapter_step950/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_final/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step100/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step1000/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step1050/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step1100/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step1150/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step1200/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step1250/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step1300/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step1350/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step1400/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step1450/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step150/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step1500/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step200/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step250/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step300/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step350/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step400/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step450/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step50/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step500/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step550/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step600/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step650/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step700/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step750/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step800/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step850/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step900/README.mdDocumentation5.2 KB —
sft_lr2e5/adapter_step950/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_final/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step100/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step1000/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step1050/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step1100/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step1150/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step1200/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step1250/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step1300/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step1350/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step1400/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step1450/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step150/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step1500/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step200/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step250/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step300/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step350/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step400/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step450/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step50/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step500/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step550/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step600/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step650/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step700/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step750/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step800/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step850/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step900/README.mdDocumentation5.2 KB —
sft_lr2e5_s7/adapter_step950/README.mdDocumentation5.2 KB —
results/dpo/metrics.jsonlOther2.0 KB —
results/dpo/train_log.jsonlOther305.2 KB —
results/multi.logOther37 B —
results/q0.logOther1.1 KB —
results/q0_rlfix.g0_step1.logOther22.3 KB —
results/q0_rlfix2.g0_step1.logOther —
results/q0_rlfix2.g0_step2.logOther32.8 KB —
results/q0_rlfix2.g0_step3.logOther1.8 KB —
results/q0_rlfix3.g0_step1.logOther32.7 KB —
results/q1.logOther1.2 KB —
results/q1_rlfix.g1_step1.logOther21.3 KB —
results/q1_rlfix2.g1_step1.logOther33.0 KB —
results/q1_rlfix2.g1_step2.logOther33.0 KB —
results/q1_rlfix3.g1_step1.logOther42.6 KB —
results/q2.logOther999 B —
results/q2_rlfix.g2_step1.logOther20.5 KB —
results/q2_rlfix2.g2_step1.logOther36.0 KB —
results/q2_rlfix2.g2_step2.logOther35.7 KB —
results/q3.logOther768 B —
results/q3_rlfix.g3_step1.logOther33.6 KB —
results/q3_rlfix.g3_step2.logOther32.8 KB —
results/q3_rlfix3.g3_step1.logOther22.1 KB —
results/rl_exact_ent/metrics.jsonlOther980 B —
results/rl_exact_ent/train_log.jsonlOther197.8 KB —
results/rl_exact_lr2e5/metrics.jsonlOther2.0 KB —
results/rl_exact_lr2e5/train_log.jsonlOther304.5 KB —
results/rl_exact_lr2e5_cont/metrics.jsonlOther2.0 KB —
results/rl_exact_lr2e5_cont/train_log.jsonlOther303.5 KB —
results/rl_exact_lr2e5_s7/metrics.jsonlOther1.0 KB —
results/rl_exact_lr2e5_s7/train_log.jsonlOther404.9 KB —
results/rl_norm_lr2e5/metrics.jsonlOther2.0 KB —
results/rl_norm_lr2e5/train_log.jsonlOther303.1 KB —
results/rl_sample_loo/metrics.jsonlOther1.0 KB —
results/rl_sample_loo/train_log.jsonlOther190.5 KB —
results/rloo_lr2e5/metrics.jsonlOther2.0 KB —
results/rloo_lr2e5/train_log.jsonlOther334.2 KB —
results/rloo_lr2e5_cont/metrics.jsonlOther2.0 KB —
results/rloo_lr2e5_cont/train_log.jsonlOther330.6 KB —
results/seq.logOther84 B —
results/sft_dense/metrics.jsonlOther1.6 KB —
results/sft_dense/train_log.jsonlOther202.9 KB —
results/sft_dense_s7/metrics.jsonlOther1.3 KB —
results/sft_dense_s7/train_log.jsonlOther203.0 KB —
results/sft_lr2e5/metrics.jsonlOther2.0 KB —
results/sft_lr2e5/train_log.jsonlOther302.1 KB —
results/sft_lr2e5_s7/metrics.jsonlOther2.0 KB —
results/sft_lr2e5_s7/train_log.jsonlOther302.0 KB —
results/step1.logOther —
.gitattributesRepository1.5 KB —

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
32.1 GB
Download from Jord Nguyen

Released by Jord Nguyen through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published32.1 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.