Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
5
14
14
ssz
ssz1111
Follow
AMRuk's profile picture
patrickNLP's profile picture
ShuangZeng's profile picture
3 followers
·
4 following
AI & ML interests
None yet
Recent Activity
reacted
to
vicgalle
's
post
with 🤝
15 days ago
Can you merge models of different sizes? ⚗️ Well, yes, if the models are somewhat compatible. Here is an experiment I did. I wanted to merge two of the best performing models: https://huggingface.co/mlabonne/NeuralBeagle14-7B and https://huggingface.co/jeonsworld/CarbonVillain-en-10.7B-v4 Here is my recipe: 1. Expand the layers of NeuralBeagle to 10.7B ala frankenmerge. 2. DPO-tune the previous model with a high-quality preference dataset, https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs 3. Merge the previous model with CarbonVillain (needs —allow-crimes in mergekit! 🔪) And here is the resulting model, CarbonBeagle-11B, which ranked top in the leaderboard for its size class: https://huggingface.co/vicgalle/CarbonBeagle-11B
reacted
to
vicgalle
's
post
with 🤯
15 days ago
Can you merge models of different sizes? ⚗️ Well, yes, if the models are somewhat compatible. Here is an experiment I did. I wanted to merge two of the best performing models: https://huggingface.co/mlabonne/NeuralBeagle14-7B and https://huggingface.co/jeonsworld/CarbonVillain-en-10.7B-v4 Here is my recipe: 1. Expand the layers of NeuralBeagle to 10.7B ala frankenmerge. 2. DPO-tune the previous model with a high-quality preference dataset, https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs 3. Merge the previous model with CarbonVillain (needs —allow-crimes in mergekit! 🔪) And here is the resulting model, CarbonBeagle-11B, which ranked top in the leaderboard for its size class: https://huggingface.co/vicgalle/CarbonBeagle-11B
upvoted
an
article
15 days ago
Merge Large Language Models with mergekit
View all activity
Organizations
ssz1111
's activity
All
Models
Datasets
Spaces
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
liked
3 models
about 1 month ago
ssz1111/CANOE-Qwen2.5-7B
Text Generation
•
8B
•
Updated
Apr 15, 2025
•
7
•
1
ssz1111/CANOE-LLaMA3-8B
Text Generation
•
8B
•
Updated
Apr 15, 2025
•
8
•
1
ssz1111/FaithLens
8B
•
Updated
Dec 23, 2025
•
21.6k
•
2
liked
a model
5 months ago
ssz1111/CANOE-Qwen2.5-14B
Text Generation
•
15B
•
Updated
Apr 15, 2025
•
1
•
2
liked
4 models
6 months ago
ssz1111/NOVA-LLaMA-3-8B-AlpacaGPT4-15percent
Text Generation
•
Updated
May 12, 2025
•
1
•
1
ssz1111/NOVA-LLaMA-3-8B-Alpaca-15percent
Text Generation
•
Updated
May 12, 2025
•
1
•
1
ssz1111/NOVA-LLaMA-3-8B-AlpacaGPT4-5percent
Text Generation
•
Updated
May 12, 2025
•
1
•
1
ssz1111/NOVA-LLaMA-3-8B-Alpaca-5percent
Text Generation
•
Updated
May 12, 2025
•
1
•
1
liked
6 models
about 1 year ago
ssz1111/GATEAU-1k-10k
Updated
Dec 13, 2024
•
1
ssz1111/GATEAU-1k-100k
Updated
Dec 13, 2024
•
1
ssz1111/GATEAU-3k-100k
Updated
Dec 13, 2024
•
1
•
1
ssz1111/GATEAU-5k-10k
Updated
Dec 13, 2024
•
1
ssz1111/GATEAU-3k-10k
Updated
Dec 13, 2024
•
1
ssz1111/GATEAU-5k-100k
Updated
Dec 13, 2024
•
1
•
1