Hugging Face's logo

arcee-ai
/
Trinity-Large-Preview

Text Generation
Transformers
Safetensors
afmoe
conversational
custom_code
Eval Results
Model card Files
xet
 Community
6
lckr commited on
Commit
75d2869
·
verified ·
1 Parent(s): 5d844e7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -50,6 +50,7 @@ More details on the training of Trinity Large are available in the [technical re
50
  The Trinity Large family consists of three checkpoints from the same training run:
51
 
52
  - **Trinity-Large-Preview** (this release): Lightly post-trained, chat-ready model undergoing active RL
 
53
  - **[Trinity-Large-TrueBase](https://huggingface.co/arcee-ai/Trinity-Large-TrueBase)**: 10T-token pre-anneal pretraining checkpoint
54
  - **[Trinity-Large-Base](https://huggingface.co/arcee-ai/Trinity-Large-Base)**: Full 17T-token pretrained foundation model with mid-training anneals
55
 
 
50
  The Trinity Large family consists of three checkpoints from the same training run:
51
 
52
  - **Trinity-Large-Preview** (this release): Lightly post-trained, chat-ready model undergoing active RL
53
+ - **[Trinity-Large-Thinking](https://huggingface.co/arcee-ai/Trinity-Large-Thinking)**: Reasoning-optimized, agentic post-training with extended chain-of-thought
54
  - **[Trinity-Large-TrueBase](https://huggingface.co/arcee-ai/Trinity-Large-TrueBase)**: 10T-token pre-anneal pretraining checkpoint
55
  - **[Trinity-Large-Base](https://huggingface.co/arcee-ai/Trinity-Large-Base)**: Full 17T-token pretrained foundation model with mid-training anneals
56