Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
lunahr
/
thea-3b-25r
like
1
Text Generation
Transformers
Safetensors
KingNish/reasoning-base-20k
lunahr/thea-name-overrides
English
llama
text-generation-inference
trl
sft
reasoning
llama-3
conversational
Eval Results
Inference Endpoints
License:
llama3.2
Model card
Files
Files and versions
Community
1
Train
Deploy
Use this model
163a51e
thea-3b-25r
Commit History
v2 is now available!
163a51e
verified
lunahr
commited on
11 days ago
updated username
f2ecf3b
verified
lunahr
commited on
17 days ago
Update name in config.json
aa30551
verified
Piotr Zalewski
commited on
Oct 17
Remove truncation
d0dcf39
lunahr
commited on
Oct 16
Name override with rsLoRA(rank=128, alpha=256)
b66ed89
lunahr
commited on
Oct 16
Adding Evaluation Results (
#1
)
fa02e86
verified
Piotr Zalewski
leaderboard-pr-bot
commited on
Oct 14
Latest version
aa1299e
verified
Piotr Zalewski
commited on
Oct 13
Add reasoning to tokenizer
4661fb3
verified
Piotr Zalewski
commited on
Oct 11
wrote the readme
02d731b
verified
Piotr Zalewski
commited on
Oct 11
Upload merged BF16 model
0ab895c
verified
Piotr Zalewski
commited on
Oct 11
initial commit
3f3636d
verified
Piotr Zalewski
commited on
Oct 11