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
Quazim0t0
/
Escarda-Docling-126M
Like
1
Image-to-Text
Safetensors
docling
doctags
document-understanding
vision-language-model
jepa
hrm
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
Escarda-Docling-126M
643 MB
Ctrl+K
Ctrl+K
1 contributor
History:
6 commits
Quazim0t0
Document engram repair
edc573c
verified
2 months ago
__pycache__
Escarda-Docling-126M: JEPA+HRM docling VLM + full Byrne comparison
2 months ago
examples
Escarda-Docling-126M: JEPA+HRM docling VLM + full Byrne comparison
2 months ago
lm
Engram-repaired base LM weights (bit-exact rescale + broadcast)
2 months ago
vision
Escarda-Docling-126M: JEPA+HRM docling VLM + full Byrne comparison
2 months ago
weights
Engram repair + short distill: n-gram memory now populated (was 1 bucket)
2 months ago
.gitattributes
Safe
1.52 kB
initial commit
2 months ago
README.md
5.05 kB
Document engram repair
2 months ago
anyres.py
Safe
2.1 kB
Escarda-Docling-126M: JEPA+HRM docling VLM + full Byrne comparison
2 months ago
config_escarda.py
Safe
7.88 kB
Escarda-Docling-126M: JEPA+HRM docling VLM + full Byrne comparison
2 months ago
doctags_vocab_meta.json
Safe
1.05 kB
Escarda-Docling-126M: JEPA+HRM docling VLM + full Byrne comparison
2 months ago
family_lora.py
Safe
4.65 kB
Escarda-Docling-126M: JEPA+HRM docling VLM + full Byrne comparison
2 months ago
generate.py
Safe
6.86 kB
Harness: KV-cached decode with exact engram window, verified token-identical to full recompute (which was O(n^2))
2 months ago
hrm_lora.py
Safe
3.27 kB
Escarda-Docling-126M: JEPA+HRM docling VLM + full Byrne comparison
2 months ago
modeling_byrne_embed.py
Safe
47.5 kB
Escarda-Docling-126M: JEPA+HRM docling VLM + full Byrne comparison
2 months ago
modeling_escarda.py
Safe
41.3 kB
Escarda-Docling-126M: JEPA+HRM docling VLM + full Byrne comparison
2 months ago
requirements.txt
Safe
60 Bytes
Escarda-Docling-126M: JEPA+HRM docling VLM + full Byrne comparison
2 months ago
spike_tokenizer.py
Safe
5.71 kB
Escarda-Docling-126M: JEPA+HRM docling VLM + full Byrne comparison
2 months ago
tokenizer.json
Safe
263 kB
Escarda-Docling-126M: JEPA+HRM docling VLM + full Byrne comparison
2 months ago
tokenizer_doctags.json
Safe
268 kB
Escarda-Docling-126M: JEPA+HRM docling VLM + full Byrne comparison
2 months ago
vlm_model.py
Safe
6.51 kB
Escarda-Docling-126M: JEPA+HRM docling VLM + full Byrne comparison
2 months ago
