SmolFactory

Sleeping

App Files Files Community

SmolFactory

Commit History

Aug 11, 2025

07:54
re adds the join us shield

Tonic

eb53d98
07:52
updates gradio versions

Tonic

b4091c6
07:35
updates readmes

Tonic

78a7472
07:33
Update README.md

Tonic

Verified signature
7aa5e49

Aug 10, 2025

18:24
adds how to instructions

Tonic

1fcb282
18:15
adds image and title to the interface

Tonic

35c4baa
18:05
adds tabbed interface, advanced mode, connectors

Tonic

cb30cda
17:53
adds interface linkage so updates work correctly

Tonic

943cfba
17:45
adds interface.py improvements to the flow and tab

Tonic

4b9e23f
17:23
improves interface flow

Tonic

a8fc78d
16:05
improves interface.py

Tonic

b867691
15:51
adds a lot of improvements to launch.sh and demo spaces and secures read token at demo launch

Tonic

36b8703
11:19
adds hf compatible readme yaml

Tonic

68b0972
11:16
adds hf compatible readme yaml

Tonic

93d0081
11:12
improves spaces deployment , configuration for custom settings , adds interface for spaces deployment

Tonic

5f8b28d

Aug 9, 2025

10:12
adds steps logging + parsing - woops

Tonic

a509b8b
00:16
adds experiment id fix

Tonic

c560f4f

Aug 8, 2025

23:16
adds normalized variables on update

Tonic

0f12d91
22:35
propagates changes

Tonic

468cb10
22:28
adds improved dataset utils with new interface

Tonic

b172ca3
22:08
adds packing argument to gpt oss custom config

Tonic

401f18e
21:58
fixes circular import

Tonic

6995e18
21:37
add configs to _init_.py

Tonic

63ce7d6
21:35
solves import error

Tonic

c238a70
21:16
non destructive dataset operations

Tonic

cf628aa
20:48
adds imports and forces monitoring

Tonic

190d843
19:34
adds scheduler stuff and hopes for the best with track tonic

Tonic

d455d12
18:44
adds local and remote training monitors to config

Tonic

71db310
17:05
improve dataset utils non destructive writes

Tonic

924581c
16:41
adds parameters to medical config

Tonic

81f39f1
16:12
adds parameters to medical config

Tonic

b4f1cb3
16:12
adds parameters to medical config

Tonic

c68717e
16:05
adds improved dev and system prompts to o1-medical

Tonic

fc29a51
16:03
adds improved launch for reasoning gpt-oss configs and new config for medical reasoning

Tonic

0ded6bb
10:12
adds improved dataset utils in tracktonic

Tonic

b11b94b
10:10
adds optimizations for faster training

Tonic

3331c7f
09:41
adds a100 memory optimized

Tonic

fa9560d
08:24
adds template files , adds non destructive dataset updates

Tonic

d47568c
06:53
adds flash attention 3 kernel

Tonic

cb276d8

Aug 7, 2025

23:24
adapt lr_scheduler according to trl version

Tonic

976e218
23:03
sets min_lr

Tonic

7f45871
22:36
increases batchsize and gradient accumulation steps in memory optimized

Tonic

4e59f6d
22:35
increases max samples in memory optimized

Tonic

8b56686
22:28
adds better launch.sh and eval / test splits auto

Tonic

0fa6045
22:03
adds repoid only based on repo name, adds version-robust sfttrainer

Tonic

665844a
21:52
coerce akk numeric config values to safe values

Tonic

c346dad
21:35
adds defensive programming (boo) and adaptations based on transformer versions

Tonic

97dacc7
21:15
improves launcher with model family and defaults based on options, updates trl trainer , removes trl config paths by switching to trainingarguments class , tokenizer parameters updated to sfttrainer , resolves evaluation_strategy error

Tonic

598357a
21:02
hide all tokens in logs, never persist to disk, remove max_seq_length from config, add to trainer

Tonic

eb9e91f
20:41
changes default model repo name + adds non default option

Tonic

c23e2f5

Commit History

Aug 11, 2025

re adds the join us shield

updates gradio versions

updates readmes

Update README.md

Aug 10, 2025

adds how to instructions

adds image and title to the interface

adds tabbed interface, advanced mode, connectors

adds interface linkage so updates work correctly

adds interface.py improvements to the flow and tab

improves interface flow

improves interface.py

adds a lot of improvements to launch.sh and demo spaces and secures read token at demo launch

adds hf compatible readme yaml

adds hf compatible readme yaml

improves spaces deployment , configuration for custom settings , adds interface for spaces deployment

Aug 9, 2025

adds steps logging + parsing - woops

adds experiment id fix

Aug 8, 2025

adds normalized variables on update

propagates changes

adds improved dataset utils with new interface

adds packing argument to gpt oss custom config

fixes circular import

add configs to _init_.py

solves import error

non destructive dataset operations

adds imports and forces monitoring

adds scheduler stuff and hopes for the best with track tonic

adds local and remote training monitors to config

improve dataset utils non destructive writes

adds parameters to medical config

adds parameters to medical config

adds parameters to medical config

adds improved dev and system prompts to o1-medical

adds improved launch for reasoning gpt-oss configs and new config for medical reasoning

adds improved dataset utils in tracktonic

adds optimizations for faster training

adds a100 memory optimized

adds template files , adds non destructive dataset updates

adds flash attention 3 kernel

Aug 7, 2025

adapt lr_scheduler according to trl version

sets min_lr

increases batchsize and gradient accumulation steps in memory optimized

increases max samples in memory optimized

adds better launch.sh and eval / test splits auto

adds repoid only based on repo name, adds version-robust sfttrainer

coerce akk numeric config values to safe values

adds defensive programming (boo) and adaptations based on transformer versions

improves launcher with model family and defaults based on options, updates trl trainer , removes trl config paths by switching to trainingarguments class , tokenizer parameters updated to sfttrainer , resolves evaluation_strategy error

hide all tokens in logs, never persist to disk, remove max_seq_length from config, add to trainer

changes default model repo name + adds non default option