Lora & full finetune experiments on r1 distills to generate python code for math problems
Ram
0-hero
AI & ML interests
All work on this profile is personal
Organizations
Training GPT-2 with different types of positional encodings
DPO & Fine-tuned models with function calling on the Matter-0.2 dataset. 8x22B, 32B, 7B sizes
DPO & Fine-tuned models with function calling on the Matter-0.1 dataset. "Matter-0.1-7B-boost-DPO-preview" recommended for chat
-
0-hero/Matter-0.1-7B-boost-DPO-preview
Text Generation • 7B • Updated • 1 • 3 -
munish0838/Matter-0.1-7B-boost-DPO-preview-GGUF
Text Generation • 7B • Updated • 63 -
0-hero/Matter-0.1-7B-DPO-preview
Text Generation • 7B • Updated • 2 • 1 -
QuantFactory/Matter-0.1-7B-DPO-preview-GGUF
Text Generation • 7B • Updated • 40 • 1
Lora & full finetune experiments on r1 distills to generate python code for math problems
Training GPT-2 with different types of positional encodings
DPO & Fine-tuned models with function calling on the Matter-0.1 dataset. "Matter-0.1-7B-boost-DPO-preview" recommended for chat
-
0-hero/Matter-0.1-7B-boost-DPO-preview
Text Generation • 7B • Updated • 1 • 3 -
munish0838/Matter-0.1-7B-boost-DPO-preview-GGUF
Text Generation • 7B • Updated • 63 -
0-hero/Matter-0.1-7B-DPO-preview
Text Generation • 7B • Updated • 2 • 1 -
QuantFactory/Matter-0.1-7B-DPO-preview-GGUF
Text Generation • 7B • Updated • 40 • 1
DPO & Fine-tuned models with function calling on the Matter-0.2 dataset. 8x22B, 32B, 7B sizes