Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
2564.6
TFLOPS
1
1
32
Ronan Takizawa
PRO
ronantakizawa
Follow
MISMOOR's profile picture
PrinceZaman's profile picture
Drewhampton7654's profile picture
22 followers
·
144 following
ronantakizawa
ronantakizawa
ronantakizawa
AI & ML interests
OSS Contributor @ Google AI, Databricks, Apache. 100k+ followers online
Recent Activity
upvoted
an
article
about 12 hours ago
Uncensor any LLM with abliteration
reacted
to
their
post
with 🔥
about 12 hours ago
Excited to announce 4 AWQ quantized models from #AllenAI! 🎉 Molmo-7B-D AWQ (14GB→5GB): Efficient VLM performing between GPT-4V and GPT-4o on academic benchmarks, with just 6.1% perplexity degradation. MolmoAct-7B-D AWQ (14GB→6GB): Specialized robotic manipulation model reduced by ~57%. Molmo-72B AWQ (145GB→38GB): VLM with Qwen2-72B decoder that performs competitively with GPT-4, achieving only 10.5% perplexity degradation while saving 107GB of memory. OLMo-2-32B-Instruct AWQ (64GB→17GB): LLM post-trained on Tülu 3 with 3% perplexity degradation while saving ~50GB. All VLMs only had their text models quantized. https://huggingface.co/ronantakizawa/molmo-7b-d-awq https://huggingface.co/ronantakizawa/molmoact-7b-d-awq https://huggingface.co/ronantakizawa/molmo-72b-awq https://huggingface.co/ronantakizawa/olmo2-32b-instruct-awq
posted
an
update
1 day ago
Excited to announce 4 AWQ quantized models from #AllenAI! 🎉 Molmo-7B-D AWQ (14GB→5GB): Efficient VLM performing between GPT-4V and GPT-4o on academic benchmarks, with just 6.1% perplexity degradation. MolmoAct-7B-D AWQ (14GB→6GB): Specialized robotic manipulation model reduced by ~57%. Molmo-72B AWQ (145GB→38GB): VLM with Qwen2-72B decoder that performs competitively with GPT-4, achieving only 10.5% perplexity degradation while saving 107GB of memory. OLMo-2-32B-Instruct AWQ (64GB→17GB): LLM post-trained on Tülu 3 with 3% perplexity degradation while saving ~50GB. All VLMs only had their text models quantized. https://huggingface.co/ronantakizawa/molmo-7b-d-awq https://huggingface.co/ronantakizawa/molmoact-7b-d-awq https://huggingface.co/ronantakizawa/molmo-72b-awq https://huggingface.co/ronantakizawa/olmo2-32b-instruct-awq
View all activity
Organizations
ronantakizawa
's activity
All
Models
Datasets
Spaces
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
liked
a dataset
1 day ago
ronantakizawa/Finance-Instruct-500k-Japanese
Viewer
•
Updated
1 day ago
•
518k
•
22
•
1
liked
2 datasets
3 days ago
nick007x/github-code-2025
Viewer
•
Updated
8 days ago
•
147M
•
8.8k
•
62
ronantakizawa/japanese-text-difficulty-2level
Viewer
•
Updated
18 days ago
•
1.59k
•
37
•
1
liked
a dataset
4 days ago
Josephgflowers/Finance-Instruct-500k
Viewer
•
Updated
Mar 1
•
518k
•
1.73k
•
199
liked
2 models
5 days ago
ronantakizawa/molmo-72b-awq
Image-Text-to-Text
•
11B
•
Updated
5 days ago
•
51
•
1
ronantakizawa/olmo2-32b-instruct-awq
Text Generation
•
5B
•
Updated
6 days ago
•
2
•
1
liked
4 models
6 days ago
allenai/OLMo-2-0325-32B-Instruct
Text Generation
•
32B
•
Updated
Mar 14
•
16.9k
•
147
ronantakizawa/molmo-7b-d-awq
Image-Text-to-Text
•
2B
•
Updated
6 days ago
•
14
•
1
ronantakizawa/molmoact-7b-d-awq
Image-Text-to-Text
•
2B
•
Updated
6 days ago
•
3
•
1
allenai/Llama-3.1-Tulu-3-405B
Text Generation
•
406B
•
Updated
Feb 10
•
139
•
109
liked
2 models
7 days ago
ronantakizawa/battery-placement
Robotics
•
Updated
Jun 14
•
2
•
1
ronantakizawa/idefics3-8b-llama3-awq
Image-Text-to-Text
•
2B
•
Updated
7 days ago
•
4
•
1
liked
2 models
9 days ago
ronantakizawa/SmolVLM-Instruct-gptq
Image-Text-to-Text
•
0.8B
•
Updated
5 days ago
•
57
•
1
ronantakizawa/SmolVLM-Instruct-awq
Image-Text-to-Text
•
0.8B
•
Updated
5 days ago
•
58
•
1
liked
a dataset
10 days ago
sbintuitions/JCommonsenseQA
Viewer
•
Updated
28 days ago
•
10.1k
•
63
•
1
liked
a model
13 days ago
tencent/HunyuanVideo
Text-to-Video
•
Updated
Mar 6
•
2.14k
•
•
2.06k
liked
a model
14 days ago
Qwen/Qwen-Image-Edit
Image-to-Image
•
Updated
Aug 25
•
178k
•
•
2.04k
liked
a model
15 days ago
ronantakizawa/higgs-llama-3-70b-awq
71B
•
Updated
14 days ago
•
31
•
1
liked
a model
16 days ago
bosonai/Higgs-Llama-3-70B
Text Generation
•
71B
•
Updated
Aug 20, 2024
•
8.35k
•
•
227
liked
a model
17 days ago
ronantakizawa/phi-4-reasoning-awq
15B
•
Updated
17 days ago
•
41
•
1
Load more