Esper 3 is a DevOps, architecture, code, and general reasoning finetune for Qwen 3!
Valiant Labs
company
AI & ML interests
transformation
Recent Activity
Organization Card
At Valiant Labs, we build frontier intelligence and release it open source. For everyone to use.
Esper 3 is finetuned on high-difficulty coding, architecture, DevOps, and general reasoning:
ValiantLabs/DeepSeek-R1-0528-Qwen3-8B-Esper3
Cobalt 2 is finetuned on high-difficulty math and general reasoning:
Shining Valiant 2 is finetuned on high-quality science, complex queries, and general chat:
ValiantLabs/Llama3.1-8B-ShiningValiant2
ValiantLabs/Llama3.1-70B-ShiningValiant2
ValiantLabs/Llama3.2-3B-ShiningValiant2
Check out our website!
Contact us via email at [email protected]
Collections
3
Our earlier models.
-
ValiantLabs/Llama2-70B-ShiningValiant
Text Generation • Updated • 22 • 74 -
ValiantLabs/Llama2-13B-ShiningValiant
Text Generation • Updated • 21 • 11 -
ValiantLabs/CodeLlama-13B-Fireplace
Text Generation • Updated • 21 • 2 -
ValiantLabs/CodeLlama-70B-Esper
Text Generation • Updated • 13 • 2
models
20
ValiantLabs/DeepSeek-R1-0528-Qwen3-8B-Esper3
Text Generation
•
Updated
•
40
•
1
ValiantLabs/Qwen3-14B-Cobalt2
Text Generation
•
Updated
•
38
•
2
ValiantLabs/Qwen3-14B-Esper3
Text Generation
•
Updated
•
94
•
11
ValiantLabs/Qwen3-8B-Esper3
Text Generation
•
Updated
•
472
•
15
ValiantLabs/Qwen3-4B-Esper3
Text Generation
•
Updated
•
5.46k
•
8
ValiantLabs/Llama3.1-8B-Esper2
Text Generation
•
Updated
•
12
•
2
ValiantLabs/Llama3.1-8B-Enigma
Text Generation
•
Updated
•
46
•
10
ValiantLabs/Llama3.1-8B-Cobalt
Text Generation
•
Updated
•
1.42k
•
6
ValiantLabs/Llama3.1-8B-Fireplace2
Text Generation
•
Updated
•
1.43k
•
6
ValiantLabs/Llama3-70B-Fireplace
Text Generation
•
Updated
•
5.56k
•
3
datasets
0
None public yet