Modifying Large Language Model Post-Training for Diverse Creative Writing
Paper
•
2503.17126
•
Published
•
36
Ninefid
den0620
AI & ML interests
I just examine models
Recent Activity
upvoted
a
paper
10 days ago
Modifying Large Language Model Post-Training for Diverse Creative
Writing
upvoted
a
paper
10 days ago
ReSearch: Learning to Reason with Search for LLMs via Reinforcement
Learning
liked
a model
about 1 month ago
mistralai/Mistral-Small-3.1-24B-Instruct-2503
Organizations
None yet
den0620's activity
upvoted
2
papers
10 days ago
liked
a
model
about 1 month ago
reacted to
mlabonne's
post with 👍
about 1 month ago
Post
9153
✂️ AutoAbliteration
I made a Colab notebook to automatically abliterate models.
It's quite general, so you can do interesting stuff like blocking a given language in the model outputs.
💻 Colab: https://colab.research.google.com/drive/1RmLv-pCMBBsQGXQIM8yF-OdCNyoylUR1?usp=sharing
I made a Colab notebook to automatically abliterate models.
It's quite general, so you can do interesting stuff like blocking a given language in the model outputs.
💻 Colab: https://colab.research.google.com/drive/1RmLv-pCMBBsQGXQIM8yF-OdCNyoylUR1?usp=sharing
liked
9
models
about 1 month ago
google/gemma-3-1b-pt
Text Generation
•
Updated
•
181k
•
106
google/gemma-3-1b-it
Text Generation
•
Updated
•
1.89M
•
334
google/gemma-3-4b-pt
Image-Text-to-Text
•
Updated
•
57.7k
•
67
google/gemma-3-4b-it
Image-Text-to-Text
•
Updated
•
617k
•
462
google/gemma-3-12b-pt
Image-Text-to-Text
•
Updated
•
49.6k
•
44
google/gemma-3-12b-it
Image-Text-to-Text
•
Updated
•
344k
•
332
google/gemma-3-27b-pt
Image-Text-to-Text
•
Updated
•
20.2k
•
91
google/gemma-3-27b-it
Image-Text-to-Text
•
Updated
•
590k
•
•
1.24k
CohereLabs/c4ai-command-a-03-2025
Text Generation
•
Updated
•
14.9k
•
•
346
upvoted
a
collection
about 1 month ago
liked
2
models
about 1 month ago
liked
a
model
3 months ago
reacted to
onekq's
post with 🚀
3 months ago
Post
1335
Mistral Small 3 is SUPER fast, and highest score for 20+b model, but still 11 points below Qwen 2.5 coder 32b.
I believe specialty model is the future. The more you know what to do with the model, the better bang you can get for your buck. If Mistral scopes this small model to coding only, I'm confident they can beat Qwen.
One day my leaderboard will be dominated by smol models excellent on one thing, not monolithic ones costing $$$. And I'm looking forward to that.
onekq-ai/WebApp1K-models-leaderboard
I believe specialty model is the future. The more you know what to do with the model, the better bang you can get for your buck. If Mistral scopes this small model to coding only, I'm confident they can beat Qwen.
One day my leaderboard will be dominated by smol models excellent on one thing, not monolithic ones costing $$$. And I'm looking forward to that.
onekq-ai/WebApp1K-models-leaderboard
- 1 reply
reacted to
fdaudens's
post with ❤️
3 months ago
Post
9202
Yes, DeepSeek R1's release is impressive. But the real story is what happened in just 7 days after:
- Original release: 8 models, 540K downloads. Just the beginning...
- The community turned those open-weight models into +550 NEW models on Hugging Face. Total downloads? 2.5M—nearly 5X the originals.
The reason? DeepSeek models are open-weight, letting anyone build on top of them. Interesting to note that the community focused on quantized versions for better efficiency & accessibility. They want models that use less memory, run faster, and are more energy-efficient.
When you empower builders, innovation explodes. For everyone. 🚀
The most popular community model? @bartowski 's DeepSeek-R1-Distill-Qwen-32B-GGUF version — 1M downloads alone.
- Original release: 8 models, 540K downloads. Just the beginning...
- The community turned those open-weight models into +550 NEW models on Hugging Face. Total downloads? 2.5M—nearly 5X the originals.
The reason? DeepSeek models are open-weight, letting anyone build on top of them. Interesting to note that the community focused on quantized versions for better efficiency & accessibility. They want models that use less memory, run faster, and are more energy-efficient.
When you empower builders, innovation explodes. For everyone. 🚀
The most popular community model? @bartowski 's DeepSeek-R1-Distill-Qwen-32B-GGUF version — 1M downloads alone.
- 5 replies
liked
a
model
4 months ago
