Paul Lemaistre PRO
paulml
AI & ML interests
TTS - LLM - Agents |
Lead Dev @ TW3 Partners
Recent Activity
upvoted
an
article
7 days ago
Supercharge your OCR Pipelines with Open Models
upvoted
an
article
8 days ago
How I Built Lightning-Fast Vector Search for Legal Documents
reacted
to
ronantakizawa's
post
with 👍
8 days ago
Introducing AWQ and GPTQ quantized versions of SmolVLM from Hugging Face!
These models only had their text models quantized, and had a 50% model size reduction (4GB~2GB) while keeping model degradation under 1% on the DocVQA benchmark.
#huggingface #smolvlm #smollm
https://huggingface.co/ronantakizawa/SmolVLM-Instruct-awq
https://huggingface.co/ronantakizawa/SmolVLM-Instruct-gptq
Organizations
Model Fine-Tuning
2
#2 opened 9 months ago
by
mrodriguesoliv
Adding Evaluation Results
#1 opened over 1 year ago
by
leaderboard-pr-bot
update config.json vocab_size to tokenizer length
5
#1 opened over 1 year ago
by
sparsh35
Great model
2
#4 opened over 1 year ago
by
RedLeader721
The model is not performing well.
👍
1
25
#1 opened over 1 year ago
by
Liangmingxin
Quantized model
5
#3 opened over 1 year ago
by
MaziyarPanahi
Chat template?
4
#14 opened over 1 year ago
by
XeIaso
Probably the new best "base" model to use to merge
3
#1 opened over 1 year ago
by
paulml
The quantized version still has the INST spamming problem
1
#1 opened over 1 year ago
by
Xhatz
INST problem?
3
#2 opened over 1 year ago
by
Slayery
Adding Evaluation Results
#3 opened over 1 year ago
by
paulml
chat template and context?
1
#1 opened over 1 year ago
by
cognitivetech
Update README.md
#1 opened over 1 year ago
by
PaulTW3
Update README.md
#1 opened over 1 year ago
by
PaulTW3