21 10 348

cstr

CrispStrobe

AI & ML interests

None yet

Recent Activity

liked a model 4 days ago

Mungert/Qwen2.5-VL-3B-Instruct-GGUF

liked a model 4 days ago

rednote-hilab/dots.ocr

liked a dataset 21 days ago

DeepMount00/italian_conversations

View all activity

Organizations

liked 2 models 4 days ago

Mungert/Qwen2.5-VL-3B-Instruct-GGUF

Image-Text-to-Text • 3B • Updated Jun 15 • 3.26k • 20

rednote-hilab/dots.ocr

Image-Text-to-Text • 3B • Updated about 1 hour ago • 4.51k • 447

liked a dataset 21 days ago

DeepMount00/italian_conversations

Viewer • Updated 21 days ago • 21.1k • 1.56k • 27

liked a Space 21 days ago

FutureBench Leaderboard

🔮

Display and analyze prediction leaderboard data

liked a model 27 days ago

HuggingFaceTB/SmolLM3-3B

Text Generation • 3B • Updated 10 days ago • 843k • • 638

liked 2 models 2 months ago

bartowski/Teuken-7B-instruct-research-v0.4-GGUF

Text Generation • 7B • Updated Nov 26, 2024 • 1.01k • 4

openGPT-X/Teuken-7B-instruct-commercial-v0.4

Text Generation • 7B • Updated Dec 11, 2024 • 1.57k • 74

updated a model 2 months ago

cstr/mt0-large-Q4_K_M-GGUF

Text Generation • 1B • Updated Jun 4 • 7

published a model 2 months ago

cstr/mt0-large-Q4_K_M-GGUF

Text Generation • 1B • Updated Jun 4 • 7

liked a model 2 months ago

csukuangfj/kokoro-multi-lang-v1_0

Updated Apr 20 • 3

New activity in aihpi/F5-TTS-German 2 months ago

mlx conversion

#5 opened 2 months ago by

cstr

updated a model 2 months ago

cstr/aihpi_f5_german_mlx_q4

Text-to-Speech • Updated May 27

published a model 2 months ago

cstr/aihpi_f5_german_mlx_q4

Text-to-Speech • Updated May 27

liked a model 2 months ago

MultiLlasa/Llasa-1B-Multilingual-German

1B • Updated Mar 8 • 10 • 10

liked 2 models 3 months ago

HKUSTAudio/xcodec2

Audio-to-Audio • 0.8B • Updated Feb 23 • 17.2k • 80

SebastianBodza/Kartoffel_Orpheus-3B_german_natural-v0.1

Text-to-Speech • 3B • Updated May 17 • 140 • 13

reacted to hesamation's post with 👀 4 months ago

Post

2932

this paper has been blowing up
they train an open-source multimodal LLM (InternVL3) that can compete with GPT-4o and Claude 3.5 Sonnet by:
> training text and vision on a single stage
> a novel V2PE positional encoding
> SFT & mixed preference optimization
Paper: InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models (2504.10479)
> test-time scaling