German-English models, mostly merged, some sft/dpo
cstr
cstr
AI & ML interests
None yet
Recent Activity
reacted
to
hesamation's
post
with 👀
19 days ago
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: https://huggingface.co/papers/2504.10479
> test-time scaling
liked
a model
26 days ago
Revai/reverb-diarization-v2
liked
a model
26 days ago
diarizers-community/speaker-segmentation-fine-tuned-callhome-deu
Organizations
Collections
2
spaces
5
models
96
cstr/paraphrase-multilingual-MiniLM-L12-v2-mlx
Sentence Similarity
•
Updated
•
4
cstr/DeepSeek-R1-Distill-Llama-8B-abliterated-Q4_K_M-GGUF
Updated
•
3
cstr/aya-expanse-8b-Q4_K_M-GGUF
Updated
•
4
cstr/Ministral-8B-Instruct-2410-GGUF
Updated
•
5
•
1
cstr/whisper-large-v3-turbo-german-ggml
Automatic Speech Recognition
•
Updated
cstr/whisper-large-v3-turbo-german-int8_float32
Automatic Speech Recognition
•
Updated
•
28
•
1
cstr/salamandra-7b-instruct-GGUF
Text Generation
•
Updated
•
36
•
2
cstr/whisper-large-v3-turbo-int8_float32
Automatic Speech Recognition
•
Updated
•
64
cstr/llama3.1-8b-spaetzle-v119
Updated
•
1
cstr/llama3.1-8b-spaetzle-v90
Updated
•
4
•
2
datasets
9
cstr/mistralorpo_conv
Viewer
•
Updated
•
21.6k
•
15
cstr/phi3orpo
Viewer
•
Updated
•
2.62k
•
17
cstr/capybara_de_sharegpt
Viewer
•
Updated
•
16k
•
14
cstr/hermes_de_sharegpt
Viewer
•
Updated
•
205k
•
14
cstr/Capybara-de-snippets
Updated
•
81
cstr/intel_orca_dpo_pairs_de
Viewer
•
Updated
•
12.9k
•
48
•
2
cstr/ultrafeedback-binarized-preferences-cleaned-de-2
Viewer
•
Updated
•
664
•
16
cstr/ultrafeedback-binarized-preferences-cleaned-de
Viewer
•
Updated
•
8.93k
•
12
cstr/ultrafeedback-binarized-preferences-cleaned-de-3
Viewer
•
Updated
•
3.44k
•
4