Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
Rayugacodes
/
kernelx-strategist
like
1
Safetensors
llama
Model card
Files
Files and versions
xet
Community
main
kernelx-strategist
1.49 GB
Ctrl+K
Ctrl+K
1 contributor
History:
33 commits
Rayugacodes
Blog: The Digital Traffic Jam
7d2467c
verified
11 days ago
adapter
LoRA adapter (warm-start SFT)
11 days ago
plots
Benchmark: benchmark_results.json
11 days ago
training
Training pipeline scripts
11 days ago
.gitattributes
Safe
1.64 kB
Add training plot: grpo_training.png
11 days ago
Blog.md
13.2 kB
Blog: The Digital Traffic Jam
11 days ago
KernelX_Training.ipynb
Safe
23.2 kB
Fix: keep Colab defaults, install only trl+peft with --no-deps, handle all TRL versions
11 days ago
README.md
Safe
11.4 kB
Update README with latest
11 days ago
config.json
Safe
921 Bytes
Merged strategist (warm-start + GRPO)
11 days ago
generation_config.json
Safe
132 Bytes
Merged strategist (warm-start + GRPO)
11 days ago
merges.txt
Safe
466 kB
Tokenizer
11 days ago
model.safetensors
Safe
1.45 GB
xet
Merged strategist (warm-start + GRPO)
11 days ago
special_tokens_map.json
Safe
655 Bytes
Tokenizer
11 days ago
tokenizer.json
Safe
3.52 MB
Tokenizer
11 days ago
tokenizer_config.json
Safe
3.79 kB
Tokenizer
11 days ago
train_on_hf.py
Safe
13.1 kB
GPU training script for HF
11 days ago
vocab.json
Safe
801 kB
Tokenizer
11 days ago
