TMaxxx
/

tmax-2b-v1.1

Reinforcement Learning

Model card Files Files and versions

3.78 GB

Ctrl+K

Ctrl+K

2 contributors

History: 9 commits

hamishivi's picture

Use canonical TMax-13K v1.1 dataset name

a248117 verified about 18 hours ago

.checkpoint_complete

621 Bytes
Copy files from models/TMaxxx/qwen-2b-dppo-hardened-prefilter-sc3 26 days ago
.gitattributes

1.57 kB
Copy files from models/TMaxxx/qwen-2b-dppo-hardened-prefilter-sc3 26 days ago
README.md

5.29 kB
Use canonical TMax-13K v1.1 dataset name about 18 hours ago
campaign_provenance.json

7.13 kB
Copy files from models/TMaxxx/qwen-2b-dppo-hardened-prefilter-sc3 26 days ago
chat_template.jinja

7.74 kB
Align shipped template and checkpoint selection with preserved-thinking evaluations about 19 hours ago
config.json

1.79 kB
Copy files from models/TMaxxx/qwen-2b-dppo-hardened-prefilter-sc3 26 days ago
generation_config.json

115 Bytes
Copy files from models/TMaxxx/qwen-2b-dppo-hardened-prefilter-sc3 26 days ago
model.safetensors

3.76 GB
xet

Copy files from models/TMaxxx/qwen-2b-dppo-hardened-prefilter-sc3 26 days ago
preserved_thinking.json

449 Bytes
Align shipped template and checkpoint selection with preserved-thinking evaluations about 19 hours ago
release_manifest.json

2.95 kB
Align shipped template and checkpoint selection with preserved-thinking evaluations about 19 hours ago
tokenizer.json

20 MB
xet

Copy files from models/TMaxxx/qwen-2b-dppo-hardened-prefilter-sc3 26 days ago
tokenizer_config.json

1.1 kB
Copy files from models/TMaxxx/qwen-2b-dppo-hardened-prefilter-sc3 26 days ago