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
Asilarknes
/
powergqa-778m
like
0
PyTorch
English
causal-lm
gqa
custom-architecture
sft
lima
experimental
small-llm
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
powergqa-778m
6.25 GB
Ctrl+K
Ctrl+K
1 contributor
History:
7 commits
Asilarknes
Initial upload: PowerGQA-778M ckpt_13500 (Phase19 LIMA best)
216512d
verified
about 2 months ago
checkpoints
Upload ckpt_12500 latest stable checkpoint with test report
about 2 months ago
tokenizer
Upload PowerGQA 778M checkpoint ckpt_1500
about 2 months ago
.gitattributes
Safe
1.63 kB
Initial upload: PowerGQA-778M ckpt_13500 (Phase19 LIMA best)
about 2 months ago
PowerGQA-778M.pt
1.56 GB
xet
Initial upload: PowerGQA-778M ckpt_13500 (Phase19 LIMA best)
about 2 months ago
README.md
Safe
6.28 kB
Initial upload: PowerGQA-778M ckpt_13500 (Phase19 LIMA best)
about 2 months ago
chat_template.jinja
Safe
2.43 kB
Initial upload: PowerGQA-778M ckpt_13500 (Phase19 LIMA best)
about 2 months ago
ckpt_1500.pt
1.56 GB
xet
Upload PowerGQA 778M checkpoint ckpt_1500
about 2 months ago
latest_test_ckpt12500_full.txt
Safe
30.6 kB
Upload ckpt_12500 latest stable checkpoint with test report
about 2 months ago
powergqa_config.json
Safe
531 Bytes
Upload PowerGQA 778M checkpoint ckpt_1500
about 2 months ago
powergqa_identity_sft_static_1000.jsonl
Safe
520 kB
Initial upload: PowerGQA-778M ckpt_13500 (Phase19 LIMA best)
about 2 months ago
sample_chat_manual_12300.py
Safe
3.46 kB
Initial upload: PowerGQA-778M ckpt_13500 (Phase19 LIMA best)
about 2 months ago
score_fresh_ckpt12500.txt
Safe
352 Bytes
Upload ckpt_12500 latest stable checkpoint with test report
about 2 months ago
score_holdout_ckpt12500.txt
Safe
37 Bytes
Upload ckpt_12500 latest stable checkpoint with test report
about 2 months ago
tokenizer.json
Safe
11.4 MB
xet
Initial upload: PowerGQA-778M ckpt_13500 (Phase19 LIMA best)
about 2 months ago
tokenizer_config.json
Safe
697 Bytes
Initial upload: PowerGQA-778M ckpt_13500 (Phase19 LIMA best)
about 2 months ago
train_powergqa_4090.py
Safe
93.4 kB
Initial upload: PowerGQA-778M ckpt_13500 (Phase19 LIMA best)
about 2 months ago
train_powergqa_500m.py
Safe
12.1 kB
Upload PowerGQA 778M checkpoint ckpt_1500
about 2 months ago