Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
soda-research
/
soda-4b-base
like
6
Follow
soda-research
7
Safetensors
soda-research/yodas2-mm-pretrain
soda-research/emilia-mm-pretrain
English
qwen3
audio
speech
foundation-model
next-token-prediction
tts
asr
speech-continuation
arxiv:
2602.16687
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
main
soda-4b-base
17.5 GB
1 contributor
History:
8 commits
potsawee
Update README.md
f16f830
verified
15 days ago
.gitattributes
1.57 kB
Upload model checkpoint
about 2 months ago
README.md
14.7 kB
Update README.md
15 days ago
chat_template.jinja
460 Bytes
Upload model checkpoint
about 2 months ago
config.json
2.74 kB
Upload model checkpoint
about 2 months ago
model-00001-of-00004.safetensors
4.98 GB
xet
Upload model checkpoint
about 2 months ago
model-00002-of-00004.safetensors
4.94 GB
xet
Upload model checkpoint
about 2 months ago
model-00003-of-00004.safetensors
4.94 GB
xet
Upload model checkpoint
about 2 months ago
model-00004-of-00004.safetensors
2.63 GB
xet
Upload model checkpoint
about 2 months ago
model.safetensors.index.json
31.3 kB
Upload model checkpoint
about 2 months ago
special_tokens_map.json
424 Bytes
Upload model checkpoint
about 2 months ago
tokenizer.json
20.2 MB
xet
Upload model checkpoint
about 2 months ago
tokenizer_config.json
2.84 MB
Upload model checkpoint
about 2 months ago