teknium
b2d17a44d2
Add README for server handling module and refine ReasoningConfig logic
...
- Introduced a new README.md file detailing the server handling module, including support for reasoning models, provider differences, effort level mappings, and usage examples.
- Cleaned up the ReasoningConfig class by removing unnecessary comments and clarifying logic related to reasoning injection and provider-specific requirements.
2026-01-15 07:21:53 +00:00
teknium
0e187d7869
Update completion handler documentation to clarify that reasoning config is not injected for completions, as it is only supported in chat completions.
2026-01-15 06:44:55 +00:00
pre-commit-ci[bot]
b6e24266b2
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2026-01-15 06:27:19 +00:00
teknium
0316cac8d1
Rename is_active method to is_reasoning_kwargs_active in ReasoningConfig for clarity. Update references in the class and corresponding tests to reflect this change.
2026-01-15 06:26:31 +00:00
balyan.sid@gmail.com
c56af35eaa
switch to evalbase for verifiers_eval.py
2026-01-15 11:34:40 +05:30
pre-commit-ci[bot]
39e9a233db
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2026-01-14 21:36:05 +00:00
Savage890
39f05d18fa
fix: handle nested message format in jsonl2html.py ( #308 )
2026-01-15 03:01:15 +05:30
dmahan93
9f6681be95
Merge pull request #315 from NousResearch/pre-commit-ci-update-config
...
[pre-commit.ci] pre-commit autoupdate
2026-01-14 09:02:27 -08:00
teknium
00a0f5397a
Merge branch 'add_reasoning_handling_draft' of https://github.com/NousResearch/atropos into add_reasoning_handling_draft
2026-01-14 13:38:08 +00:00
teknium
3a854cc3af
fix linter
2026-01-14 13:38:04 +00:00
balyan.sid@gmail.com
57fa229846
remove unused managed_server wrapper + tese
2026-01-14 17:09:57 +05:30
balyan.sid@gmail.com
6a27e88023
use managed server
2026-01-14 17:09:01 +05:30
balyan.sid@gmail.com
32320512e8
update verifiers_server to use tokenizer_for_trainer
2026-01-13 15:00:54 +05:30
pre-commit-ci[bot]
79a55ff186
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2026-01-13 07:30:33 +00:00
teknium
2a7dd49328
Merge branch 'add_reasoning_handling_draft' of https://github.com/NousResearch/atropos into add_reasoning_handling_draft
2026-01-13 07:29:48 +00:00
teknium
b33cb7f943
A bit more updates for robustness
2026-01-13 07:29:43 +00:00
Teknium
837fc237ee
Merge branch 'main' into add_reasoning_handling_draft
2026-01-12 09:45:38 -08:00
teknium
6aba5244b8
ReasoningConfig documentation to clarify dependency on effort and max_tokens settings. This update specifies that enabling either of these parameters requires reasoning in OpenRouter to be set to Enabled.
2026-01-12 17:45:19 +00:00
teknium
21504537fc
revive _get_server_base_url
2026-01-12 16:49:38 +00:00
pre-commit-ci[bot]
38d0283e8c
[pre-commit.ci] pre-commit autoupdate
...
updates:
- [github.com/astral-sh/ruff-pre-commit: v0.14.10 → v0.14.11](https://github.com/astral-sh/ruff-pre-commit/compare/v0.14.10...v0.14.11 )
2026-01-12 16:41:30 +00:00
balyan.sid@gmail.com
a1d1e7d7fe
fix env_args, dataset/prompt loading
2026-01-12 10:39:43 +05:30
pre-commit-ci[bot]
7907ffd0ad
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2026-01-12 05:05:11 +00:00
balyan.sid@gmail.com
49687304ef
fix verifiers conflict
2026-01-12 10:34:05 +05:30
balyan.sid@gmail.com
9db6c0d1ed
added better wandb logging
2026-01-12 10:34:05 +05:30
balyan.sid@gmail.com
dceb1d8fd8
parallelize verifiers_server: use generate() for SFT, parallel
...
ManagedServer contexts for RL
2026-01-12 10:34:05 +05:30
balyan.sid@gmail.com
24b4488c60
clean up eval, pin verifiers version
2026-01-12 10:34:05 +05:30
pre-commit-ci[bot]
d98bc6d9fc
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2026-01-12 10:34:05 +05:30
balyan.sid@gmail.com
294b980625
add tests for AtroposManagedClient
2026-01-12 10:34:05 +05:30
balyan.sid@gmail.com
cf636595d2
rework server and eval for rl rollout. add in asyncmanagedserver for
...
verifiers
2026-01-12 10:34:05 +05:30
pre-commit-ci[bot]
3449a4c23d
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2026-01-12 10:34:05 +05:30
balyan.sid@gmail.com
5b09ad86f4
update readme, add sft-datagen to verifiers_server
2026-01-09 19:20:41 +05:30
balyan.sid@gmail.com
636715bb08
add wandb to eval
2026-01-09 16:51:19 +05:30
balyan.sid@gmail.com
dda85430da
fix docstrings
2026-01-09 16:25:44 +05:30
balyan.sid@gmail.com
9d5cd2b593
fix: improve verifiers environments consistency and correctness
...
- verifiers_server.py: consistent dataset column selection for train/test,
remove redundant comments, preserve float precision for scores
- verifiers_eval.py: add env_config_cls, fix constructor signature to match
BaseEnv (slurm bool), make stub methods raise NotImplementedError
2026-01-09 16:21:12 +05:30
balyan.sid@gmail.com
b62c416130
make verifiers deps optional and update README
2026-01-09 14:37:50 +05:30
balyan.sid@gmail.com
ed826de724
wip: verifiers integration
2026-01-09 14:21:03 +05:30
Teknium
a7a87a33e4
Merge pull request #301 from PLippmann/feat/sql-query-env
...
Feat/sql query env
2026-01-06 06:46:02 -08:00
PLippmann
5a130a3a5b
Quote fix
2026-01-06 15:14:26 +01:00
PLippmann
7d8123a526
Missing initialization
2026-01-06 15:14:26 +01:00
PLippmann
c927794248
Add SQL Query Generation Environment
2026-01-06 15:14:26 +01:00
Teknium
6d79d4c7ad
Merge pull request #290 from NousResearch/add-eval-runner
...
add eval runner
2026-01-05 15:48:45 -08:00
Teknium
11ebecd93f
Merge branch 'main' into add-eval-runner
2026-01-05 15:46:39 -08:00
teknium
cb6bf37e68
update name of eval example
2026-01-05 23:46:27 +00:00
Teknium
64b201af52
Merge pull request #234 from NousResearch/reverse-text-env
...
Add reversed text environment
2026-01-05 15:39:28 -08:00
teknium
1fa5c3eee4
lint it
2026-01-05 23:37:37 +00:00
Teknium
3ef206e013
Merge branch 'main' into reverse-text-env
2026-01-05 15:33:43 -08:00
pre-commit-ci[bot]
6cfcbdf4d5
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2026-01-05 23:20:47 +00:00
teknium
e1ece3e64e
Add reasoning configuration support across server implementations
...
- Updated server classes (OpenAIServer, SGLangServer, TrlVllmServer, VLLMServer) to accept a ReasoningConfig parameter during initialization.
- Enhanced ReasoningConfig to allow flexible max_tokens without strict validation, accommodating varying provider limits.
- Implemented reasoning configuration injection in APIServer methods for chat and completion handling.
- Updated tests to reflect changes in max_tokens validation logic.
This commit integrates reasoning capabilities into the server handling architecture, improving compatibility with diverse reasoning models.
2026-01-05 23:20:01 +00:00
Teknium
d2330633b3
Merge pull request #293 from JustKitting/gsm8k-fix
...
Fix missing logprob
2026-01-03 04:01:48 -08:00
Teknium
46beb71e4b
Merge branch 'main' into gsm8k-fix
2026-01-03 03:58:51 -08:00
