Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
DebateLabKIT
/
Phi-4-Argunaut-1-HIRPO
like
0
Follow
DebateLab at KIT
14
Text Generation
Transformers
Safetensors
DebateLabKIT/arguments-and-debates
English
llama
logic
argumentation
critical-thinking
argument-mapping
Generated from Trainer
trl
rlvr
hirpo
conversational
text-generation-inference
arxiv:
2302.05206
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
Phi-4-Argunaut-1-HIRPO
29.3 GB
1 contributor
History:
113 commits
ggbetz
Update README.md
69b99b6
verified
8 days ago
.gitattributes
Safe
1.52 kB
initial commit
3 months ago
README.md
Safe
3.24 kB
Update README.md
8 days ago
chat_template.jinja
Safe
2.5 kB
Model save
3 months ago
config.json
Safe
820 Bytes
Update config.json
9 days ago
generation_config.json
Safe
147 Bytes
Model save
3 months ago
merges.txt
Safe
917 kB
Model save
3 months ago
model-00001-of-00006.safetensors
4.93 GB
xet
Model save
9 days ago
model-00002-of-00006.safetensors
4.95 GB
xet
Model save
9 days ago
model-00003-of-00006.safetensors
4.9 GB
xet
Model save
9 days ago
model-00004-of-00006.safetensors
4.95 GB
xet
Model save
9 days ago
model-00005-of-00006.safetensors
4.95 GB
xet
Model save
9 days ago
model-00006-of-00006.safetensors
4.62 GB
xet
Model save
9 days ago
model.safetensors.index.json
Safe
29.9 kB
Model save
3 months ago
special_tokens_map.json
Safe
570 Bytes
Model save
3 months ago
tokenizer.json
Safe
7.15 MB
Model save
3 months ago
tokenizer_config.json
Safe
17.5 kB
Model save
3 months ago
vocab.json
Safe
1.61 MB
Model save
3 months ago