Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
PJMixers-Dev
/
LLaMa-3.2-Instruct-JankMix-v0.2-SFT-HailMary-v0.1-KTO-3B
like
0
Follow
Peanut Jar Mixers Development
8
Safetensors
PJMixers-Dev/HailMary-v0.1-KTO
English
llama
Eval Results
License:
llama3.2
Model card
Files
Files and versions
Community
Train
main
LLaMa-3.2-Instruct-JankMix-v0.2-SFT-HailMary-v0.1-KTO-3B
/
images
1 contributor
History:
1 commit
xzuyn
Upload 6 files
991817b
verified
2 months ago
train_grad_norm.png
Safe
162 kB
Upload 6 files
2 months ago
train_logits_chosen_rejected.png
Safe
315 kB
Upload 6 files
2 months ago
train_logps_chosen_rejected.png
Safe
289 kB
Upload 6 files
2 months ago
train_loss.png
Safe
146 kB
Upload 6 files
2 months ago
train_rewards_chosen_rejected.png
Safe
151 kB
Upload 6 files
2 months ago
train_rewards_margins.png
Safe
133 kB
Upload 6 files
2 months ago
