DeepScaleR-1.5B-Preview is a language model fine-tuned from DeepSeek-R1-Distilled-Qwen-1.5B. Beats o1 preview in math.
ThomasBaruzier
ThomasBaruzier
AI & ML interests
None yet
Recent Activity
liked
a model
5 days ago
mistralai/Mistral-Small-3.1-24B-Instruct-2503
liked
a model
8 days ago
ibm-granite/granite-3.2-8b-instruct
liked
a model
9 days ago
sesame/csm-1b
Organizations
None yet
Collections
10
models
35
ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-7B-v1.1-GGUF
Text Generation
•
Updated
•
545
ThomasBaruzier/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF
Text Generation
•
Updated
•
730
ThomasBaruzier/DeepScaleR-1.5B-Preview-GGUF
Updated
•
972
ThomasBaruzier/Qwen2.5-72B-Instruct-GGUF
Text Generation
•
Updated
•
885
ThomasBaruzier/Llama-3.3-70B-Instruct-GGUF
Updated
•
2.55k
•
1
ThomasBaruzier/Qwen2.5-Coder-7B-Instruct-GGUF
Text Generation
•
Updated
•
460
ThomasBaruzier/Qwen2.5-Coder-3B-Instruct-GGUF
Text Generation
•
Updated
•
460
ThomasBaruzier/Qwen2.5-Coder-0.5B-Instruct-GGUF
Text Generation
•
Updated
•
516
•
1
ThomasBaruzier/Qwen2.5-Coder-1.5B-Instruct-GGUF
Text Generation
•
Updated
•
322
ThomasBaruzier/DeepScaleR-1.5B-Preview-abliterated-GGUF
Updated
•
542