DPO & Fine-tuned models with function calling on the Matter-0.1 dataset. "Matter-0.1-7B-boost-DPO-preview" recommended for chat
Ram
0-hero
AI & ML interests
All work on this profile is personal
Organizations
Collections
2
models
25
0-hero/fineweb-edu-100BT-GPT2-tokenized
Updated
0-hero/fineweb-edu-10BT-GPT2-tokenized
Updated
0-hero/Matter-0.2-7B-DPO
Text Generation
•
Updated
•
22
•
3
0-hero/Matter-0.2-32B
Text Generation
•
Updated
•
21
•
3
0-hero/Matter-0.2-8x22B
Text Generation
•
Updated
•
8
0-hero/OLMo-50M-Mixture-of-Depths-Bitnet
Updated
•
1
0-hero/Matter-0.1-Slim-7B-B
Text Generation
•
Updated
•
72
0-hero/Matter-0.1-Slim-7B-C-DPO
Text Generation
•
Updated
•
73
0-hero/mistral-speech-to-text
Text Generation
•
Updated
•
4
0-hero/mistral-speech-to-text-preview
Text Generation
•
Updated
•
13
datasets
12
0-hero/distilabel-math-preference-dpo
Viewer
•
Updated
•
2.42k
•
48
0-hero/lj_speech_with_spectogram_conversations
Viewer
•
Updated
•
13.1k
•
41
•
1
0-hero/lj_speech_with_spectogram
Viewer
•
Updated
•
13.1k
•
54
•
1
0-hero/Matter-0.2-alpha
Viewer
•
Updated
•
2.52M
•
60
•
3
0-hero/Matter-0.1
Viewer
•
Updated
•
2.25M
•
120
•
53
0-hero/Matter-0.1-Slim-D
Viewer
•
Updated
•
1.32M
•
56
0-hero/Matter-0.1-Slim-C
Viewer
•
Updated
•
343k
•
46
0-hero/Matter-0.1-Slim-B
Viewer
•
Updated
•
308k
•
45
•
1
0-hero/Matter-0.1-Slim-A
Viewer
•
Updated
•
285k
•
49
0-hero/prompt-perfect
Preview
•
Updated
•
295
•
28