Quazim0t0
/

Escarda-Rewrite

Text Generation

prompt-optimization

query-rewriting

Model card Files Files and versions

Escarda-Rewrite

393 MB

Ctrl+K

Ctrl+K

1 contributor

History: 6 commits

Quazim0t0's picture

Fix engram n-gram lookups during cached decode: add engram_context_ids so single-token steps match full-sequence computation

8e92c65 about 14 hours ago

__pycache__
Escarda-Rewrite 86M prompt optimizer (v2 final) + loader + card 9 days ago
.gitattributes

1.57 kB
Upload Escarda-LLMs.png with huggingface_hub 8 days ago
Escarda-LLMs.png

3.04 MB
xet

Upload Escarda-LLMs.png with huggingface_hub 8 days ago
README.md

2.18 kB
Upload README.md with huggingface_hub 8 days ago
config.json

1.74 kB
Escarda-Rewrite 86M prompt optimizer (v2 final) + loader + card 9 days ago
config.py

7.88 kB
Escarda-Rewrite 86M prompt optimizer (v2 final) + loader + card 9 days ago
model.safetensors

389 MB
xet

Update to v3: adds employment-law coverage (paycheck/wages/fired/non-compete now route to Legal Advisor); no regression on other roles 9 days ago
model_v2.py

41.8 kB
Fix engram n-gram lookups during cached decode: add engram_context_ids so single-token steps match full-sequence computation about 14 hours ago
rewrite.py

2.4 kB
Escarda-Rewrite 86M prompt optimizer (v2 final) + loader + card 9 days ago
special_tokens_map.json

504 Bytes
Escarda-Rewrite 86M prompt optimizer (v2 final) + loader + card 9 days ago
spike_tokenizer.py

5.4 kB
Escarda-Rewrite 86M prompt optimizer (v2 final) + loader + card 9 days ago
tokenizer.json

263 kB
Escarda-Rewrite 86M prompt optimizer (v2 final) + loader + card 9 days ago
tokenizer_config.json

4.57 kB
Escarda-Rewrite 86M prompt optimizer (v2 final) + loader + card 9 days ago