Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Spaces:
Abhi2280
/
Math-Escalation-Trainer
like
0
Running
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
Math-Escalation-Trainer
43.7 kB
Ctrl+K
Ctrl+K
2 contributors
History:
46 commits
Abhishek Jadhav
feat: accuracy-v4 — 2x steps, LR 1e-5, dense rewards, LoRA r=64, gradient clip
fe0b07c
2 months ago
.gitattributes
Safe
1.52 kB
initial commit
2 months ago
.gitignore
46 Bytes
Expose 12 hyperparameters as a Gradio form, no auto-start
2 months ago
Dockerfile
Safe
942 Bytes
Force-remove llm_blender; pre-populate sys.modules mock before trl import
2 months ago
README.md
957 Bytes
Skip Hub create_repo if model repo exists; README one-time 403 fix
2 months ago
app.py
Safe
8.07 kB
feat: accuracy-v4 — 2x steps, LR 1e-5, dense rewards, LoRA r=64, gradient clip
2 months ago
blog.md
Safe
10.5 kB
Add blog.md
2 months ago
requirements.txt
Safe
213 Bytes
Mock llm_blender to bypass broken transformers import in TRL
2 months ago
train_worker.py
Safe
21.4 kB
feat: accuracy-v4 — 2x steps, LR 1e-5, dense rewards, LoRA r=64, gradient clip
2 months ago
